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

    Neuronpedia

    INDEX
    Explanations

    abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hust
    -0.07
    ANGO
    -0.07
     acclaimed
    -0.07
     !***
    -0.07
    !("
    -0.06
    باس
    -0.06
    IMENT
    -0.06
     warmly
    -0.06
    眼泪
    -0.06
     abuse
    -0.06
    POSITIVE LOGITS
    atitis
    0.07
    上前
    0.07
    illegal
    0.07
     הקוד
    0.07
    _PLAYER
    0.07
    -pad
    0.07
     Permit
    0.07
    oblins
    0.07
    ™
    0.07
    velop
    0.07
    Act Density 0.546%

    No Known Activations