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

    Neuronpedia

    INDEX
    Explanations

    Low VOCs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Trock
    0.40
     Chí
    0.37
     constate
    0.36
     Watkins
    0.36
     الحركه
    0.35
    atr
    0.35
    ް
    0.35
    ляция
    0.35
     鞋
    0.35
     रिवीजन
    0.34
    POSITIVE LOGITS
    فت
    0.38
    swire
    0.37
    底部
    0.36
    thand
    0.36
    সে
    0.35
    Given
    0.35
    given
    0.35
    SIBLE
    0.35
     lastName
    0.35
     ethereum
    0.35
    Act Density 0.000%

    No Known Activations