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

    Neuronpedia

    INDEX
    Explanations

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emerge
    -0.07
    AC
    -0.06
    ければ
    -0.06
     sliders
    -0.06
    CFG
    -0.06
    Header
    -0.06
    EdgeInsets
    -0.06
    های
    -0.06
     fractional
    -0.06
    ADER
    -0.06
    POSITIVE LOGITS
     생
    0.07
     Newfoundland
    0.07
     représent
    0.06
    uits
    0.06
    /tool
    0.06
     noi
    0.06
    …↵↵
    0.06
    }">↵
    0.06
    icts
    0.06
    aná
    0.06
    Act Density 0.152%

    No Known Activations