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

    Neuronpedia

    INDEX
    Explanations

    Grant and Grover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    0.66
    ول
    0.59
    c
    0.58
    اب
    0.56
    و
    0.55
    ov
    0.55
     سال
    0.53
    у
    0.52
    ாய்
    0.52
    ati
    0.51
    POSITIVE LOGITS
     ritor
    0.57
     überprü
    0.55
    Turtle
    0.54
    +"|
    0.54
     imagine
    0.54
     convoluted
    0.54
     httpClient
    0.54
    ücklich
    0.53
     juggling
    0.53
     sord
    0.53
    Act Density 0.000%

    No Known Activations