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

    Neuronpedia

    INDEX
    Explanations

    see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Volvo
    0.95
    ́u
    0.85
    elligence
    0.83
    uca
    0.82
    3
    0.82
    Porsche
    0.81
    UM
    0.80
    했다
    0.80
    ENSE
    0.79
    Chrome
    0.79
    POSITIVE LOGITS
    тка
    1.01
    лую
    0.92
     ھ
    0.89
     períodos
    0.88
    دیای
    0.86
    tedir
    0.85
     hamp
    0.84
    ي
    0.84
     difund
    0.83
     fes
    0.83
    Act Density 0.000%

    No Known Activations