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

    Neuronpedia

    INDEX
    Explanations

    GPT, cloud, loading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    绪
    0.48
    עה
    0.45
    蟎
    0.44
    郸
    0.44
    ńskim
    0.43
    commision
    0.42
    SleepHours
    0.42
     gonorrhea
    0.42
    امه
    0.42
    lineContainer
    0.42
    POSITIVE LOGITS
     related
    0.44
    y
    0.42
     z
    0.41
    ,
    0.40
    …
    0.38
    fatal
    0.38
     vital
    0.38
     sim
    0.37
     to
    0.37
     model
    0.37
    Act Density 0.000%

    No Known Activations