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

    Neuronpedia

    INDEX
    Explanations

    plus signs and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ari
    0.68
    ING
    0.63
    art
    0.59
    ă
    0.59
    ara
    0.57
    )।
    0.55
    ة
    0.54
    September
    0.54
    Author
    0.52
    Assistant
    0.52
    POSITIVE LOGITS
     (+)
    1.09
     (+
    0.87
    (+)
    0.83
     +,
    0.82
     $+
    0.82
    ++
    0.81
    ,+
    0.80
    .+
    0.79
    ">+</
    0.78
    /+
    0.78
    Act Density 0.081%

    No Known Activations