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

    Neuronpedia

    INDEX
    Explanations

    100% or full states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    skraft
    0.46
     मोठ्या
    0.45
     ৩
    0.45
     *,
    0.44
     수를
    0.44
     около
    0.44
    \}.
    0.43
    0.43
    ಳ್ಳ
    0.43
    overleftarrow
    0.43
    POSITIVE LOGITS
     percent
    0.71
     Zero
    0.64
     zero
    0.63
     perfetto
    0.61
     ZERO
    0.59
     Percent
    0.57
     percents
    0.57
     Fully
    0.56
     perfeito
    0.55
     zéro
    0.55
    Act Density 0.037%

    No Known Activations