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

    Neuronpedia

    INDEX
    Explanations

    debate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    psych
    -0.07
     �
    -0.07
    osg
    -0.07
    -0.07
    勤
    -0.07
    $f
    -0.06
    "G
    -0.06
    Nil
    -0.06
    Ownership
    -0.06
    _EXTERNAL
    -0.06
    POSITIVE LOGITS
     debate
    0.12
     debates
    0.10
     Debate
    0.09
     debated
    0.07
    vote
    0.07
     Vote
    0.07
     همیشه
    0.07
    	db
    0.07
     rebuild
    0.07
     Senate
    0.07
    Act Density 0.005%

    No Known Activations