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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بس
    -0.07
    ctp
    -0.06
    „To
    -0.06
     plural
    -0.06
     Basis
    -0.06
    slot
    -0.06
    +xml
    -0.06
     Antworten
    -0.06
     lekker
    -0.06
     Ở
    -0.06
    POSITIVE LOGITS
    _ALWAYS
    0.07
     charities
    0.06
    hp
    0.06
    hk
    0.06
    得
    0.06
    stripe
    0.06
    스티
    0.06
     Veterans
    0.06
    qs
    0.06
    aption
    0.06
    Act Density 0.001%

    No Known Activations