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
    カー
    -0.07
     جامع
    -0.06
     çat
    -0.06
    .sk
    -0.06
    rows
    -0.06
     mij
    -0.06
     reconciliation
    -0.06
     разом
    -0.06
    竜
    -0.06
     texto
    -0.06
    POSITIVE LOGITS
     irreversible
    0.06
    Participants
    0.06
    ONY
    0.06
     Alps
    0.06
    είτε
    0.06
     Taxes
    0.06
    (parse
    0.06
    妇
    0.06
    gr
    0.06
     QList
    0.06
    Act Density 0.000%

    No Known Activations