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

    Neuronpedia

    INDEX
    Explanations

    letter of the alphabet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ষ্টিত
    0.50
     dialing
    0.43
    terminate
    0.41
    Terminate
    0.41
     uvijek
    0.41
     craz
    0.40
    diver
    0.40
     sick
    0.40
     madness
    0.40
     dwa
    0.40
    POSITIVE LOGITS
    河北
    0.59
     écrite
    0.49
    '
    0.49
     Symbols
    0.48
    r
    0.47
     Updated
    0.47
     Respondents
    0.47
    s
    0.47
    ị
    0.46
    us
    0.46
    Act Density 0.001%

    No Known Activations