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

    Neuronpedia

    INDEX
    Explanations

    itis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dive
    -0.07
     Enterprises
    -0.07
     Deep
    -0.07
     keyPressed
    -0.07
    ())
↵
↵
    -0.06
     Unter
    -0.06
    bec
    -0.06
     дво
    -0.06
    vere
    -0.06
     آنان
    -0.06
    POSITIVE LOGITS
     espec
    0.06
     Dangerous
    0.06
    evil
    0.06
    	action
    0.06
    ٫
    0.06
    _dis
    0.06
    .TYPE
    0.06
    テ
    0.06
    ฎ
    0.06
    mitted
    0.06
    Act Density 0.000%

    No Known Activations