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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hamas
    -0.08
    amm
    -0.07
    enger
    -0.07
     nghĩa
    -0.06
    curacy
    -0.06
     withstand
    -0.06
    integr
    -0.06
     Unicode
    -0.06
    =set
    -0.06
    yw
    -0.06
    POSITIVE LOGITS
    Rate
    0.07
    =i
    0.06
    Per
    0.06
    ！”↵↵
    0.06
     Poss
    0.06
    OnInit
    0.06
    가지
    0.06
    <|start_header_id|>
    0.06
     Mal
    0.06
    गढ
    0.06
    Act Density 0.000%

    No Known Activations