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

    Neuronpedia

    INDEX
    Explanations

    lists ending in conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xBE>
    0.62
    á
    0.61
    áme
    0.59
     têm
    0.59
    ą
    0.58
    ían
    0.57
     جميعا
    0.57
     čtyř
    0.57
     μόνο
    0.56
     personnalité
    0.56
    POSITIVE LOGITS
     and
    0.85
    f
    0.68
    and
    0.64
    h
    0.63
    פ
    0.61
    v
    0.57
    U
    0.55
     a
    0.54
    I
    0.54
    (
    0.52
    Act Density 0.658%

    No Known Activations