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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вполне
    -0.08
     neboť
    -0.07
    をお
    -0.07
    NIL
    -0.06
    meden
    -0.06
     मद
    -0.06
    Comp
    -0.06
    Picker
    -0.06
     ave
    -0.06
    .po
    -0.06
    POSITIVE LOGITS
     güvenilir
    0.07
    essential
    0.06
    lasyon
    0.06
    رفت
    0.06
     Italy
    0.06
     domination
    0.06
    -profile
    0.06
     dikkat
    0.06
     approaches
    0.06
    'nda
    0.06
    Act Density 0.064%

    No Known Activations