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

    Neuronpedia

    INDEX
    Explanations

    scientific citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chu
    -0.07
    IME
    -0.06
     <$
    -0.06
     Nurse
    -0.06
    (DE
    -0.06
     ViewHolder
    -0.06
    
    -0.06
     adaptive
    -0.06
    ategic
    -0.06
    .Connect
    -0.06
    POSITIVE LOGITS
    -таки
    0.08
    CppObject
    0.07
    uvre
    0.06
    .red
    0.06
    -Un
    0.06
    少女
    0.06
     attracting
    0.06
    CONST
    0.06
    kees
    0.06
     hecho
    0.06
    Act Density 0.013%

    No Known Activations