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
    .Cho
    -0.07
     shading
    -0.06
    sects
    -0.06
     discrepan
    -0.06
    Sys
    -0.06
     atroc
    -0.06
    resco
    -0.06
     consect
    -0.06
    Tit
    -0.06
    ，即
    -0.06
    POSITIVE LOGITS
    -market
    0.07
    -important
    0.07
     Uploaded
    0.07
    --;↵↵
    0.06
     اخبار
    0.06
    _ratio
    0.06
    D
    0.06
    apollo
    0.06
     useful
    0.06
    _props
    0.06
    Act Density 0.000%

    No Known Activations