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

    Neuronpedia

    INDEX
    Explanations

    response to queries about individual or usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Už
    0.45
    ה
    0.44
     stärker
    0.43
    к
    0.43
     Beginn
    0.42
    др
    0.42
    ensitive
    0.41
    тету
    0.41
    ט
    0.41
     conferring
    0.40
    POSITIVE LOGITS
    ota
    0.49
    লন
    0.46
    Tian
    0.44
    mos
    0.44
    up
    0.43
    weixin
    0.43
    IANA
    0.43
    iana
    0.43
    alop
    0.43
    ese
    0.43
    Act Density 0.003%

    No Known Activations