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

    Neuronpedia

    INDEX
    Explanations

    convergence of specific concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Virtue
    0.40
     curves
    0.39
     journeys
    0.38
    蟳
    0.38
     parabolic
    0.37
     rosy
    0.36
     टिप्स
    0.36
    atanam
    0.36
    rst
    0.35
    蛲
    0.35
    POSITIVE LOGITS
     Erek
    0.41
    Towards
    0.41
     Towards
    0.40
    Doug
    0.39
    Dil
    0.39
    Svg
    0.38
    Elev
    0.37
    spaced
    0.37
    Daily
    0.37
    अर्ज
    0.37
    Act Density 0.000%

    No Known Activations