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

    Neuronpedia

    INDEX
    Explanations

    propositional logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    2.58
    ਮ
    2.11
    ino
    2.08
    ず
    1.95
    その
    1.95
    ারী
    1.91
    까지
    1.88
    তম
    1.88
    з
    1.88
    いた
    1.86
    POSITIVE LOGITS
    de
    2.17
     afiliados
    2.14
    ни
    2.05
     associés
    2.05
     automóviles
    1.93
     affiliates
    1.91
     اولى
    1.91
     chimiques
    1.88
     изначально
    1.88
     aritmética
    1.87
    Act Density 0.042%

    No Known Activations