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

    Neuronpedia

    INDEX
    Explanations

    identities across, the sparse, the cosplay, the partition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.16
    ′
    0.95
    ^{-(
    0.93
    '
    0.92
    но
    0.90
    age
    0.89
    ‘
    0.89
    vak
    0.85
    vori
    0.85
    umber
    0.84
    POSITIVE LOGITS
    ه
    1.19
    ഘാ
    1.01
    ی
    0.94
    )。
    0.93
     discapacidad
    0.93
    Cuenta
    0.92
     éstos
    0.91
     Noodles
    0.90
    মেঘ
    0.90
    ابه
    0.88
    Act Density 0.001%

    No Known Activations