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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [list
    -0.07
    "When
    -0.07
    nesc
    -0.07
    [counter
    -0.07
    kw
    -0.06
     tố
    -0.06
    ;";↵
    -0.06
    }↵
    -0.06
    /script
    -0.06
    Default
    -0.06
    POSITIVE LOGITS
     千
    0.07
    itech
    0.07
     timber
    0.06
     Gala
    0.06
    uffled
    0.06
    尿
    0.06
     μη
    0.06
    _secondary
    0.06
     Charleston
    0.06
     Mai
    0.06
    Act Density 0.052%

    No Known Activations