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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WoW
    -0.07
    ziehung
    -0.07
     singled
    -0.06
     religious
    -0.06
    AGIC
    -0.06
    ivial
    -0.06
     Każdy
    -0.06
    سس
    -0.06
    快递
    -0.06
     jeunes
    -0.06
    POSITIVE LOGITS
     Def
    0.07
     kettle
    0.07
    `(
    0.07
     Fitz
    0.07
     lifting
    0.06
     dropped
    0.06
    ˃
    0.06
     rightfully
    0.06
     scorer
    0.06
     specifications
    0.06
    Act Density 0.000%

    No Known Activations