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

    Neuronpedia

    INDEX
    Explanations

    preposition conjunction punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.73
    i
    0.70
    ي
    0.68
    ி
    0.58
    R
    0.56
    in
    0.55
    C
    0.55
    o
    0.54
    ו
    0.53
    燹
    0.53
    POSITIVE LOGITS
     alluring
    0.63
    ಾಗ
    0.54
    ຸດ
    0.50
    ]+
    0.50
    κει
    0.49
    ᱕
    0.49
     captivating
    0.48
    გილ
    0.48
    enean
    0.48
    }°
    0.48
    Act Density 0.000%

    No Known Activations