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

    Neuronpedia

    INDEX
    Explanations

    Taking action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lastIndex
    -0.08
    .relative
    -0.08
    express
    -0.07
    (dis
    -0.07
    絕
    -0.07
    )animated
    -0.07
    褥
    -0.06
    veget
    -0.06
     Ivy
    -0.06
     ח
    -0.06
    POSITIVE LOGITS
    .Toggle
    0.07
    antis
    0.07
     latin
    0.07
    	types
    0.07
    额度
    0.07
    能做到
    0.07
     ganze
    0.07
    抗衡
    0.07
     abbreviation
    0.07
    ibling
    0.06
    Act Density 0.121%

    No Known Activations