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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ccp
    -0.07
    ょう
    -0.07
    rones
    -0.06
     والتي
    -0.06
    اطق
    -0.06
     Cabinets
    -0.06
    PCP
    -0.06
     frail
    -0.06
    饭
    -0.06
     Stewart
    -0.06
    POSITIVE LOGITS
    itarian
    0.07
    -items
    0.06
     differed
    0.06
     Stat
    0.06
     GMO
    0.06
     �
    0.06
    .shape
    0.06
     indices
    0.06
     ﺍ
    0.06
     ска
    0.06
    Act Density 0.106%

    No Known Activations