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

    Neuronpedia

    INDEX
    Explanations

    mathematical assignments or equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.11
    a
    0.99
    er
    0.95
    ا
    0.92
    l
    0.91
    ا۔
    0.88
    样子
    0.81
    r
    0.81
    al
    0.80
    t
    0.79
    POSITIVE LOGITS
    _{
    1.78
    _{\
    1.66
    ^{\
    1.53
    ^{
    1.49
    <sub>
    1.43
    ∈
    1.37
    =\
    1.30
    '=
    1.30
    ^{*}=
    1.29
    ᵢ
    1.27
    Act Density 0.483%

    No Known Activations