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

    Neuronpedia

    INDEX
    Explanations

    reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _unknown
    -0.07
    }',
    -0.07
     negativity
    -0.07
    .mods
    -0.07
     Ctrl
    -0.06
     "{}
    -0.06
    ług
    -0.06
    crast
    -0.06
    važ
    -0.06
    	parse
    -0.06
    POSITIVE LOGITS
    Cit
    0.07
    锦
    0.07
    (separator
    0.07
     (!(
    0.07
     письмен
    0.06
    ALLE
    0.06
     down
    0.06
     REGARD
    0.06
    ladığ
    0.06
    채
    0.06
    Act Density 0.015%

    No Known Activations