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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     překvap
    -0.08
    そうな
    -0.07
    бі
    -0.07
    ắ
    -0.07
    완료
    -0.07
    이어
    -0.07
     aylık
    -0.07
    uela
    -0.07
    613
    -0.07
    /sample
    -0.06
    POSITIVE LOGITS
    \.
    0.06
     comfortable
    0.06
    �
    0.06
     Blanch
    0.06
    certificate
    0.06
     περι
    0.06
     VERSION
    0.06
    ivas
    0.06
     detectives
    0.06
    ↵                ↵
    0.06
    Act Density 0.022%

    No Known Activations