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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .singletonList
    -0.06
    setw
    -0.06
     самого
    -0.06
     unittest
    -0.06
     kter
    -0.06
     мов
    -0.06
     submissive
    -0.06
    _TAC
    -0.06
     fontFamily
    -0.06
    (std
    -0.06
    POSITIVE LOGITS
    615
    0.08
     Ottoman
    0.07
    冲
    0.06
    Updates
    0.06
    arse
    0.06
     τις
    0.06
    =↵
    0.06
    (transaction
    0.06
    biased
    0.06
    etsy
    0.06
    Act Density 0.000%

    No Known Activations