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

    Neuronpedia

    INDEX
    Explanations

    say "comma"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Selection
    -0.07
    _EXP
    -0.06
     S
    -0.06
    /U
    -0.06
    ningar
    -0.06
    maktadır
    -0.06
    veis
    -0.06
    CAP
    -0.06
     verz
    -0.06
     fret
    -0.06
    POSITIVE LOGITS
    주시
    0.07
    ูง
    0.07
    ....↵↵
    0.06
     manip
    0.06
     ensemble
    0.06
     �
    0.06
     +**************
    0.06
     ří
    0.06
     strikeouts
    0.06
    ASY
    0.06
    Act Density 0.025%

    No Known Activations