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

    Neuronpedia

    INDEX
    Explanations

    google drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.38
    n
    1.13
    ного
    1.09
    ู
    1.08
    5
    1.05
    sk
    1.03
    ί
    1.03
    па
    1.02
    f
    1.02
    .
    1.02
    POSITIVE LOGITS
     personnelle
    1.09
     شخصی
    1.09
     informe
    0.99
     paseo
    0.99
    の話
    0.97
     malice
    0.96
     personnelles
    0.91
    َی
    0.91
     legumes
    0.91
     maliciously
    0.91
    Act Density 0.009%

    No Known Activations