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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loans
    -0.07
    ӏ
    -0.07
    /ui
    -0.07
     exact
    -0.06
    .assets
    -0.06
    格會員
    -0.06
     الإمام
    -0.06
    툇
    -0.06
    做不到
    -0.06
     Actors
    -0.06
    POSITIVE LOGITS
    Usu
    0.08
    <tbody
    0.08
    provide
    0.07
    .showMessage
    0.07
     fora
    0.07
    ivers
    0.07
     subclasses
    0.07
     sharedInstance
    0.07
     curso
    0.07
    _sidebar
    0.07
    Act Density 0.156%

    No Known Activations