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

    Neuronpedia

    INDEX
    Explanations

    default

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sectarian
    -0.07
    TextInput
    -0.06
     hlavu
    -0.06
    рукту
    -0.06
    λίου
    -0.06
    ENTIC
    -0.06
     nicknamed
    -0.06
     Campo
    -0.06
     sıra
    -0.06
    ickými
    -0.06
    POSITIVE LOGITS
    .Configure
    0.07
     agile
    0.06
    _DEFINE
    0.06
    perienced
    0.06
     نام
    0.06
     Hier
    0.06
    Configs
    0.06
    	args
    0.06
     intimate
    0.06
     ی
    0.06
    Act Density 0.011%

    No Known Activations