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

    Neuronpedia

    INDEX
    Explanations

    possessive/relating

    np_max-act · gemini-2.0-flash

    The neuron responds to phrases requiring “prior written” approval or consent.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ­t
    -0.07
     version
    -0.07
    URLRequest
    -0.06
     lovely
    -0.06
    -offset
    -0.06
    ESCO
    -0.06
    obil
    -0.06
    ACKET
    -0.06
     обеспечива
    -0.06
    esy
    -0.06
    POSITIVE LOGITS
    /sys
    0.06
     statistical
    0.06
     rejecting
    0.06
    parallel
    0.06
    .clear
    0.06
    STRU
    0.06
    ρος
    0.06
     miss
    0.06
     huz
    0.06
    ssl
    0.06
    Act Density 0.003%

    No Known Activations