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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jian
    -0.07
     nec
    -0.07
     voc
    -0.07
     Bless
    -0.07
    Storyboard
    -0.07
    achine
    -0.07
     bisc
    -0.07
     Salon
    -0.06
     Basket
    -0.06
     fet
    -0.06
    POSITIVE LOGITS
    (off
    0.08
    (in
    0.08
    Out
    0.07
    .off
    0.07
    OFF
    0.07
    Up
    0.07
    ,out
    0.07
     Out
    0.07
    (out
    0.07
    左右
    0.06
    Act Density 0.040%

    No Known Activations