Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    political agreement

    np_max-act · gemini-2.0-flash

    The neuron flags language about overruling, rejecting, or going against an established recommendation, authority, or consensus.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    biographical information about politicians.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ambitious
    -0.06
    <View
    -0.06
     noble
    -0.06
    られる
    -0.06
    responseObject
    -0.06
    ogeneity
    -0.06
    logg
    -0.06
     EPA
    -0.06
     dich
    -0.06
    (horizontal
    -0.06
    POSITIVE LOGITS
     Protector
    0.06
     acknow
    0.06
     stup
    0.06
     Socorro
    0.06
      
↵
    0.06
     glfw
    0.06
     Česk
    0.06
     عز
    0.06
     który
    0.06
    Sac
    0.06
    Act Density 0.027%

    No Known Activations