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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     метал
    -0.07
    庼
    -0.07
     cleric
    -0.06
    ליק
    -0.06
    𝐂
    -0.06
     grapes
    -0.06
    뚝
    -0.06
     scant
    -0.06
    lette
    -0.06
     Blades
    -0.06
    POSITIVE LOGITS
    WithType
    0.08
     hydrated
    0.07
    配资
    0.07
    .fhir
    0.07
    慎
    0.07
    ethe
    0.07
    Focus
    0.07
    PerPage
    0.06
     TRADE
    0.06
    派人
    0.06
    Act Density 0.009%

    No Known Activations