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

    Neuronpedia

    INDEX
    Explanations

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     builders
    -0.07
     cu
    -0.07
     bou
    -0.07
    [prop
    -0.06
    ουσ
    -0.06
    (operator
    -0.06
     granddaughter
    -0.06
     melanch
    -0.06
    _AMOUNT
    -0.06
    _route
    -0.06
    POSITIVE LOGITS
    虫
    0.07
     ddl
    0.06
    纪
    0.06
    感
    0.06
     Prep
    0.06
    皆
    0.06
    출장샵
    0.06
     plano
    0.06
     ":
    0.06
     Его
    0.06
    Act Density 0.000%

    No Known Activations