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

    Neuronpedia

    INDEX
    Explanations

    survival

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gas
    -0.08
     Pleasant
    -0.08
    AMY
    -0.07
    zp
    -0.07
    .FindControl
    -0.07
    镁
    -0.07
    槐
    -0.07
     Timber
    -0.07
     Barrett
    -0.07
     Fan
    -0.07
    POSITIVE LOGITS
     ripping
    0.07
     (_)
    0.07
    irting
    0.07
    uyo
    0.07
    女の
    0.07
    们都
    0.07
    者は
    0.07
     erotico
    0.07
    rising
    0.06
    орт
    0.06
    Act Density 0.060%

    No Known Activations