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

    Neuronpedia

    INDEX
    Explanations

    URLs and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rec
    -0.07
    remen
    -0.06
    asics
    -0.06
    Salvar
    -0.06
     stolen
    -0.06
    _lengths
    -0.06
    301
    -0.06
    üne
    -0.06
     hs
    -0.06
     المو
    -0.06
    POSITIVE LOGITS
    _#{
    0.07
    ()))↵
    0.06
    вав
    0.06
    .IP
    0.06
     Opera
    0.06
    Floating
    0.06
     ηλεκ
    0.06
     columnist
    0.06
     ترجم
    0.06
    ']↵↵↵
    0.06
    Act Density 0.218%

    No Known Activations