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

    Neuronpedia

    INDEX
    Explanations

    informative text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FUNC
    -0.07
    rts
    -0.06
    -0.06
    )].
    -0.06
     souls
    -0.06
    	type
    -0.06
    466
    -0.05
    '],['
    -0.05
    ')↵↵
    -0.05
     dayan
    -0.05
    POSITIVE LOGITS
     peru
    0.07
    shortcode
    0.07
    halt
    0.07
     agregar
    0.07
     kể
    0.07
    _favorite
    0.07
    _range
    0.07
     midst
    0.06
    (content
    0.06
    ="./
    0.06
    Act Density 0.125%

    No Known Activations