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

    Neuronpedia

    INDEX
    Explanations

    Code configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     temples
    -0.07
    sf
    -0.07
    [b
    -0.07
    ⟹
    -0.07
    𬬱
    -0.07
     $$
    -0.07
     lounge
    -0.07
    Full
    -0.06
    Level
    -0.06
    (Messages
    -0.06
    POSITIVE LOGITS
    鲏
    0.08
    ikhail
    0.08
    	JLabel
    0.07
     (*)(
    0.07
    KANJI
    0.07
     primaries
    0.07
    umbotron
    0.06
    tsky
    0.06
     VERBOSE
    0.06
    ⚆
    0.06
    Act Density 0.025%

    No Known Activations