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

    Neuronpedia

    INDEX
    Explanations

    small medical spots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ínguez
    0.41
     gleich
    0.41
    bestroute
    0.41
     desconocido
    0.41
    inse
    0.39
     encerr
    0.38
     läuft
    0.38
     disfrut
    0.38
    igree
    0.38
     contabil
    0.38
    POSITIVE LOGITS
     target
    0.44
     violations
    0.39
     "
    0.38
    切り
    0.38
     également
    0.38
     terminals
    0.37
     symptom
    0.37
     solutions
    0.37
     الجديدة
    0.37
     hemorrh
    0.36
    Act Density 0.001%

    No Known Activations