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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tennis
    -0.07
    asa
    -0.06
    แก
    -0.06
     hears
    -0.06
    Tit
    -0.06
    .widgets
    -0.06
     Aviation
    -0.06
     Clown
    -0.06
    Exact
    -0.06
    ımıza
    -0.06
    POSITIVE LOGITS
     TreeSet
    0.07
    ـ
    0.06
    .favorite
    0.06
    0.06
     abort
    0.06
     UserControl
    0.05
     систему
    0.05
    _Callback
    0.05
     @{$
    0.05
    :numel
    0.05
    Act Density 0.003%

    No Known Activations