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

    Neuronpedia

    INDEX
    Explanations

    Substance Abuse Helpline

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raisons
    0.85
     tượng
    0.78
    يمة
    0.77
    Ба
    0.77
     actomyosin
    0.77
    วัล
    0.76
     Scientology
    0.75
    水を
    0.74
     Conan
    0.74
     Pound
    0.74
    POSITIVE LOGITS
    fourth
    0.63
    ken
    0.63
     Filter
    0.62
    oid
    0.59
     Format
    0.59
    ilen
    0.58
     filter
    0.58
    િક્
    0.56
    Filter
    0.56
    ግ
    0.55
    Act Density 0.022%

    No Known Activations