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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.52
    тельств
    0.50
     यांच्या
    0.49
    .
    0.48
     airson
    0.48
    ::
    0.47
    weise
    0.47
    чества
    0.46
    ，
    0.46
    ۔
    0.46
    POSITIVE LOGITS
    ap
    0.49
    take
    0.49
    得到
    0.47
     or
    0.47
    get
    0.46
    gets
    0.46
    ting
    0.45
    days
    0.44
     বা
    0.44
     бы
    0.44
    Act Density 0.043%

    No Known Activations