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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Done
    -0.07
    brains
    -0.07
    Des
    -0.07
    _CLUSTER
    -0.07
    Visit
    -0.07
     logits
    -0.07
    .context
    -0.07
     Prob
    -0.07
    脱离
    -0.06
     정도
    -0.06
    POSITIVE LOGITS
     scripting
    0.08
    ]=$
    0.08
    ಐ
    0.07
    filtr
    0.07
    ']}</
    0.07
    ']}
    0.07
    气息
    0.07
    最受欢迎
    0.07
     hardness
    0.06
    吩
    0.06
    Act Density 0.001%

    No Known Activations