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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,bool
    -0.08
    崇
    -0.07
    ımsız
    -0.07
     einzel
    -0.07
    Coord
    -0.07
    ,uint
    -0.06
     mails
    -0.06
     gd
    -0.06
    ipop
    -0.06
     identity
    -0.06
    POSITIVE LOGITS
    ї
    0.08
    .Chrome
    0.06
    ارف
    0.06
    aaa
    0.06
    書館
    0.06
    ):
    0.05
    �
    0.05
    ifornia
    0.05
     Pret
    0.05
     limitation
    0.05
    Act Density 0.001%

    No Known Activations