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

    Neuronpedia

    INDEX
    Explanations

    unique

    np_max-act · gemini-2.0-flash

    This neuron is effectively “dead,” never detecting or responding to any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .bed
    -0.07
     meld
    -0.06
     forums
    -0.06
     stumble
    -0.06
    ่านมา
    -0.06
     стану
    -0.06
     Kerry
    -0.06
     pinterest
    -0.06
     schemes
    -0.06
    682
    -0.06
    POSITIVE LOGITS
    cess
    0.07
     conceived
    0.07
     scho
    0.06
     někdy
    0.06
     Uniform
    0.06
    mrt
    0.06
    měr
    0.06
    \""
    0.06
     smě
    0.06
     coi
    0.06
    Act Density 0.005%

    No Known Activations