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

    Neuronpedia

    INDEX
    Explanations

    technical and domain-specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    га
    0.49
    endregion
    0.46
    я
    0.46
    さえ
    0.44
    agama
    0.44
    нии
    0.44
     انکار
    0.43
    expr
    0.42
    ör
    0.41
    ай
    0.41
    POSITIVE LOGITS
    釟
    0.48
    ⠈
    0.47
    ెండు
    0.46
     revolutions
    0.46
     మీ
    0.45
    t
    0.45
    糍
    0.45
     marchand
    0.45
     Drift
    0.44
     डेर
    0.44
    Act Density 0.000%

    No Known Activations