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

    Neuronpedia

    INDEX
    Explanations

    Disclaimers and warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "path
    -0.07
    ่ะ
    -0.07
     comedy
    -0.07
    ΟΜ
    -0.07
     accessed
    -0.06
    пис
    -0.06
    폭
    -0.06
     ACCESS
    -0.06
    lient
    -0.06
    	reload
    -0.06
    POSITIVE LOGITS
    agen
    0.07
     squirrel
    0.06
    elix
    0.06
     geld
    0.06
    _ed
    0.06
    vlc
    0.06
     revital
    0.06
    '}↵↵
    0.06
    .handleChange
    0.06
    .setLevel
    0.06
    Act Density 0.020%

    No Known Activations