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

    Neuronpedia

    INDEX
    Explanations

    guides and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cuits
    0.45
     thème
    0.41
    Tema
    0.41
    gifts
    0.40
     Ingrid
    0.40
     veracity
    0.38
    GLIGENCE
    0.38
     marít
    0.38
    示す
    0.38
     scritta
    0.38
    POSITIVE LOGITS
     willingly
    0.46
     항상
    0.40
     constantly
    0.39
     perme
    0.39
     ಎಲ್ಲಾ
    0.38
    ethash
    0.38
     постоянно
    0.38
     samping
    0.38
     impenetr
    0.38
    ále
    0.38
    Act Density 0.000%

    No Known Activations