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

    Neuronpedia

    INDEX
    Explanations

    My and subjective states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Enough
    0.43
    relativePath
    0.40
     Average
    0.39
     ausencia
    0.39
     AVERAGE
    0.39
     Doesn
    0.39
    仞
    0.39
     ندرس
    0.38
     норма
    0.38
     Enough
    0.37
    POSITIVE LOGITS
    rony
    0.40
     Jésus
    0.40
     yellowish
    0.40
     childlike
    0.39
     gris
    0.39
    황
    0.39
    administ
    0.38
     cynicism
    0.38
     slightly
    0.38
    вой
    0.38
    Act Density 0.001%

    No Known Activations