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

    Neuronpedia

    INDEX
    Explanations

    films

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Georg
    -0.07
    [char
    -0.07
     IICIII
    -0.07
    cdn
    -0.06
     gentleman
    -0.06
    anı
    -0.06
    Escape
    -0.06
    _Data
    -0.06
     etraf
    -0.06
    形
    -0.06
    POSITIVE LOGITS
    movement
    0.07
    иж
    0.07
     водой
    0.06
     تأثیر
    0.06
    セン
    0.06
    =search
    0.06
     kInstruction
    0.06
     กรกฎ
    0.06
     movement
    0.06
     pož
    0.06
    Act Density 0.017%

    No Known Activations