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

    Neuronpedia

    INDEX
    Explanations

    instructions for formatting or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atomy
    0.40
     لهذه
    0.40
    ering
    0.39
     ov
    0.39
     Top
    0.38
     affection
    0.38
     squeezing
    0.37
     Rectangle
    0.37
     LIN
    0.37
     Obst
    0.36
    POSITIVE LOGITS
     запрос
    0.48
     powiedział
    0.44
    citealt
    0.42
    جست
    0.41
     prawdopod
    0.39
    ཝ
    0.39
    quis
    0.39
    ترح
    0.39
    ウェブ
    0.39
    螌
    0.39
    Act Density 0.000%

    No Known Activations