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

    Neuronpedia

    INDEX
    Explanations

    variety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tmp
    -0.07
    .showToast
    -0.06
     Ping
    -0.06
    =fopen
    -0.06
     MouseButton
    -0.06
    Lewis
    -0.06
     jedním
    -0.06
     nằm
    -0.06
    Ping
    -0.06
     Tcp
    -0.06
    POSITIVE LOGITS
     variety
    0.10
     varieties
    0.09
    и
    0.08
    RD
    0.08
    ardy
    0.08
    ρι
    0.08
     Variety
    0.08
    ارد
    0.08
    avor
    0.08
    Comparable
    0.07
    Act Density 0.038%

    No Known Activations