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

    Neuronpedia

    INDEX
    Explanations

    extract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clus
    -0.07
    (board
    -0.06
    Chance
    -0.06
    Act
    -0.06
     OSS
    -0.06
    Recording
    -0.06
    _classification
    -0.06
    (L
    -0.06
    bird
    -0.06
    这样的
    -0.06
    POSITIVE LOGITS
     利
    0.08
     土
    0.07
     الكتاب
    0.07
    利
    0.07
    จะเป
    0.07
     concept
    0.06
    ियन
    0.06
    ochrome
    0.06
     env
    0.06
     senha
    0.06
    Act Density 0.023%

    No Known Activations