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

    Neuronpedia

    INDEX
    Explanations

    channel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DF
    -0.07
     confidence
    -0.07
     Gus
    -0.06
    getBody
    -0.06
    _profit
    -0.06
    irm
    -0.06
    itate
    -0.06
     opera
    -0.06
    _ft
    -0.06
     설치
    -0.06
    POSITIVE LOGITS
    Nov
    0.06
     cyn
    0.06
    .COM
    0.06
     horribly
    0.06
    .central
    0.06
    �
    0.06
    nym
    0.06
     Cups
    0.06
     defensively
    0.06
    .ravel
    0.06
    Act Density 0.002%

    No Known Activations