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

    Neuronpedia

    INDEX
    Explanations

    retired, semi-retired characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abhi
    0.46
    alumno
    0.45
    anz
    0.44
    महल
    0.43
     Surv
    0.43
     नारायण
    0.43
     hızlı
    0.43
     Пу
    0.43
     aix
    0.42
    acco
    0.42
    POSITIVE LOGITS
     stink
    0.50
     stench
    0.48
     dump
    0.47
     violators
    0.47
     viol
    0.46
     disposed
    0.44
     smoke
    0.43
     chunk
    0.43
     spate
    0.43
     dumped
    0.42
    Act Density 0.002%

    No Known Activations