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

    Neuronpedia

    INDEX
    Explanations

    small differences comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAX
    -0.06
    975
    -0.06
    quisites
    -0.06
    _GEN
    -0.06
    (buff
    -0.06
    .highlight
    -0.06
    .COLOR
    -0.06
    vester
    -0.06
    .Pre
    -0.06
    calculate
    -0.06
    POSITIVE LOGITS
    官方
    0.07
     optimization
    0.07
    ">@
    0.06
    	cf
    0.06
     Hungarian
    0.06
     variations
    0.06
    ');");↵
    0.06
     lighting
    0.06
     Transparent
    0.06
     onPage
    0.06
    Act Density 0.045%

    No Known Activations