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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mcc
    -0.07
    .PackageManager
    -0.07
    RB
    -0.06
    地球
    -0.06
     Mint
    -0.06
    Nİ
    -0.06
     pitcher
    -0.06
    ্
    -0.06
    _SECURE
    -0.06
     pk
    -0.06
    POSITIVE LOGITS
     noe
    0.06
    Якщо
    0.06
     voks
    0.06
    _RANK
    0.06
     reduce
    0.06
     таким
    0.06
     zastav
    0.06
    _COMP
    0.06
     할
    0.05
    一些
    0.05
    Act Density 0.231%

    No Known Activations