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

    Neuronpedia

    INDEX
    Explanations

    ac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bott
    -0.07
    Leap
    -0.06
    727
    -0.06
    Steel
    -0.06
    ايي
    -0.06
    Mode
    -0.06
    plex
    -0.06
    alion
    -0.06
     rdr
    -0.06
    elman
    -0.06
    POSITIVE LOGITS
     因
    0.07
     Arts
    0.06
    WND
    0.06
    批
    0.06
    -con
    0.06
     ilk
    0.06
     evasion
    0.06
     EXAMPLE
    0.06
    (Cs
    0.06
     �
    0.06
    Act Density 0.005%

    No Known Activations