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

    Neuronpedia

    INDEX
    Explanations

    numbers within parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xD
    0.43
     पिछ
    0.43
     apoyo
    0.43
    apse
    0.42
    ’
    0.42
     ingles
    0.41
    Usuario
    0.40
    forge
    0.40
    Royce
    0.39
     vorbe
    0.39
    POSITIVE LOGITS
     பணி
    0.47
    稒
    0.46
    冎
    0.46
    হৃত
    0.44
    otherArchive
    0.42
    냔
    0.42
    in
    0.42
    otá
    0.42
    IZED
    0.42
    ת
    0.42
    Act Density 0.010%

    No Known Activations