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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tsunami
    -0.06
     เก
    -0.06
    _references
    -0.06
    dbg
    -0.06
    _review
    -0.06
     كيف
    -0.06
    NonNull
    -0.06
    enef
    -0.06
    _SIGNATURE
    -0.06
    )=>{↵
    -0.06
    POSITIVE LOGITS
     trespass
    0.07
     côté
    0.07
    stretch
    0.07
     mercy
    0.07
    練
    0.06
    薄
    0.06
    таб
    0.06
     государ
    0.06
     Candid
    0.06
     expenditure
    0.06
    Act Density 0.007%

    No Known Activations