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

    Neuronpedia

    INDEX
    Explanations

    numbers and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вите
    0.52
    ارس
    0.46
     hospitales
    0.45
    անի
    0.45
     сада
    0.44
     to
    0.44
    yatiti
    0.43
    ică
    0.43
    άρ
    0.43
     matem
    0.42
    POSITIVE LOGITS
    8
    0.69
    The
    0.64
    7
    0.63
    6
    0.61
    ↵
    0.60
    9
    0.60
    ↵↵
    0.59
    for
    0.59
    3
    0.57
    Dieser
    0.55
    Act Density 0.997%

    No Known Activations