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

    Neuronpedia

    INDEX
    Explanations

    BOOST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mú
    -0.07
    ci
    -0.07
    sst
    -0.06
    rors
    -0.06
    ellen
    -0.06
    一切
    -0.06
    .currency
    -0.06
    sert
    -0.06
    _TRUE
    -0.06
     '{}'
    -0.06
    POSITIVE LOGITS
    BOOST
    0.23
    	BOOST
    0.08
    (reordered
    0.07
    Ο
    0.06
     обличчя
    0.06
    ;

↵
    0.06
    DevExpress
    0.06
    .boost
    0.06
     ambient
    0.06
     ℕ
    0.06
    Act Density 0.004%

    No Known Activations