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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rients
    -0.06
     tín
    -0.06
     pulp
    -0.06
    、マ
    -0.06
    เต
    -0.06
     methods
    -0.06
    ロン
    -0.06
    matrix
    -0.06
     repro
    -0.06
     turb
    -0.06
    POSITIVE LOGITS
    etAddress
    0.07
     seas
    0.06
    Boost
    0.06
    .scal
    0.06
     Welsh
    0.06
    (resp
    0.06
    ANEL
    0.06
     Наг
    0.06
     ',↵
    0.06
     Fiji
    0.06
    Act Density 0.201%

    No Known Activations