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

    Neuronpedia

    INDEX
    Explanations

    button clicking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Score
    -0.08
    -0.08
    -score
    -0.08
    .coe
    -0.08
     pii
    -0.07
    JWT
    -0.07
    	score
    -0.07
     conform
    -0.07
    -length
    -0.07
     validators
    -0.07
    POSITIVE LOGITS
    鼠
    0.12
    (Mouse
    0.12
    .Mouse
    0.11
    Mouse
    0.11
    (mouse
    0.11
    左
    0.10
     زر
    0.10
    按钮
    0.10
     mouse
    0.10
     Mouse
    0.10
    Act Density 0.004%
    No Known Activations