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

    Neuronpedia

    INDEX
    Explanations

    stylesheet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bsites
    -0.07
    跃
    -0.07
    ア
    -0.07
    毕
    -0.06
    aks
    -0.06
    ysz
    -0.06
    lectric
    -0.06
    把他
    -0.06
    dispose
    -0.06
     alumni
    -0.06
    POSITIVE LOGITS
    适合
    0.07
    .ViewModel
    0.07
    ▰
    0.07
    .echo
    0.07
     Hartford
    0.07
     본
    0.07
    _->
    0.06
    _renderer
    0.06
     softened
    0.06
    请大家
    0.06
    Act Density 0.001%

    No Known Activations