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

    Neuronpedia

    INDEX
    Explanations

    computing, programming, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ol
    0.49
    fh
    0.48
    ]-[
    0.44
    fi
    0.42
    תר
    0.41
     filtrate
    0.41
     sinal
    0.41
    OK
    0.40
    cl
    0.40
    estring
    0.40
    POSITIVE LOGITS
    কে
    0.53
     Bradley
    0.50
    ご
    0.48
     समर्पण
    0.48
     клиентов
    0.48
     Magde
    0.46
     retaliation
    0.46
     いい
    0.46
     MLAs
    0.46
     Maureen
    0.46
    Act Density 0.038%

    No Known Activations