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

    Neuronpedia

    INDEX
    Explanations

    observations and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.48
    ність
    0.48
    ข
    0.47
     Dentro
    0.47
    เพราะ
    0.46
     écrire
    0.46
     Chew
    0.46
     Selon
    0.46
    ⓝ
    0.46
     Miet
    0.45
    POSITIVE LOGITS
     dismissed
    0.50
    ond
    0.49
     glazed
    0.46
    err
    0.45
    pre
    0.45
    omeric
    0.45
    are
    0.45
     pre
    0.44
    amburg
    0.43
    olan
    0.42
    Act Density 0.000%

    No Known Activations