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

    Neuronpedia

    INDEX
    Explanations

    cond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frightened
    -0.07
     종
    -0.07
    .d
    -0.07
    klass
    -0.06
    ubber
    -0.06
    าประ
    -0.06
    �
    -0.06
     Demon
    -0.06
     tear
    -0.06
    .ylim
    -0.06
    POSITIVE LOGITS
    .SetString
    0.07
    });↵↵↵↵
    0.06
     versatility
    0.06
    `)
    0.06
     Autodesk
    0.06
    iface
    0.06
     kredi
    0.06
    ilitary
    0.06
    backward
    0.06
    .openqa
    0.06
    Act Density 0.002%

    No Known Activations