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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    範
    -0.06
     occupations
    -0.06
     dismiss
    -0.06
    (jQuery
    -0.06
    andes
    -0.06
    κυ
    -0.06
    /s
    -0.06
     Vanilla
    -0.06
     mode
    -0.06
    坂
    -0.06
    POSITIVE LOGITS
    reste
    0.07
    -fashioned
    0.07
     variability
    0.07
    ώρα
    0.07
     brilliance
    0.07
    .xlabel
    0.07
    '],↵
    0.07
     Serie
    0.07
     veter
    0.07
    .EditText
    0.07
    Act Density 0.264%

    No Known Activations