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

    Neuronpedia

    INDEX
    Explanations

    specific follow-up questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.45
    ר
    0.44
    wald
    0.43
    Assessment
    0.43
    ||
    0.42
    {\$
    0.41
    ilage
    0.41
    োধ
    0.41
    sten
    0.40
    дава
    0.39
    POSITIVE LOGITS
     numb
    0.61
     faisant
    0.55
     размере
    0.55
     terça
    0.54
     Ubisoft
    0.54
     және
    0.53
     grinning
    0.53
     և
    0.52
    ği
    0.52
     cursing
    0.52
    Act Density 0.000%

    No Known Activations