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

    Neuronpedia

    INDEX
    Explanations

    say catch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sweet
    -0.07
    apore
    -0.07
    ](↵
    -0.07
    -setting
    -0.07
     степени
    -0.06
    command
    -0.06
    ucs
    -0.06
     labelText
    -0.06
    лив
    -0.06
    WidthSpace
    -0.06
    POSITIVE LOGITS
    Manual
    0.06
     READ
    0.06
    -shell
    0.06
     하지
    0.06
    žil
    0.06
    ;q
    0.06
     vai
    0.06
     گزارش
    0.06
     manip
    0.06
    ｜
    0.06
    Act Density 0.009%

    No Known Activations