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

    Neuronpedia

    INDEX
    Explanations

    Act

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chancellor
    -0.07
    /device
    -0.07
     RoundedRectangleBorder
    -0.07
    cedes
    -0.07
    🎥
    -0.07
    🌎
    -0.07
    inee
    -0.07
     contemplate
    -0.07
    .Join
    -0.07
    *&
    -0.07
    POSITIVE LOGITS
    Disclosure
    0.08
    '''↵↵
    0.07
    Unsafe
    0.07
    ゴ
    0.07
    תרופות
    0.06
    .decor
    0.06
    我才
    0.06
    ]+'
    0.06
    Had
    0.06
     ais
    0.06
    Act Density 0.003%

    No Known Activations