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

    Neuronpedia

    INDEX
    Explanations

    JSDoc comments and code documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    0.60
     resources
    0.60
    are
    0.59
     Resources
    0.59
    resources
    0.58
     amarilla
    0.58
    0
    0.58
    ла
    0.57
    at
    0.56
    t
    0.56
    POSITIVE LOGITS
    렌
    0.65
    ᛁ
    0.55
    Як
    0.54
    ˏ
    0.52
    ﾓ
    0.52
     SANT
    0.52
    ದಲ
    0.51
    >')
    0.51
    ೈನ
    0.51
     ascribed
    0.50
    Act Density 0.000%

    No Known Activations