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

    Neuronpedia

    INDEX
    Explanations

    all twelve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guiclass
    0.91
    umuza
    0.82
     статей
    0.82
     Artin
    0.80
    esimo
    0.78
     শব্দটি
    0.78
     NSUInteger
    0.78
     ಗುರು
    0.77
    fontSize
    0.76
     cbind
    0.76
    POSITIVE LOGITS
     its
    0.63
     floods
    0.63
    あの
    0.62
    რებული
    0.61
    ৈত
    0.60
    ท
    0.59
     Toms
    0.58
     fireworks
    0.58
     one
    0.58
    اني
    0.58
    Act Density 0.000%

    No Known Activations