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

    Neuronpedia

    INDEX
    Explanations

    concepts and their effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gram
    0.38
    long
    0.38
    my
    0.36
    general
    0.36
    English
    0.35
    Language
    0.34
    Opera
    0.34
    Bel
    0.33
    New
    0.33
    log
    0.33
    POSITIVE LOGITS
    螺旋
    0.36
    盉
    0.36
    篑
    0.36
    θούν
    0.35
    栉
    0.35
     textura
    0.35
     coiled
    0.34
    ὺ
    0.34
    യിലേക്ക്
    0.34
     কঠ
    0.33
    Act Density 0.000%

    No Known Activations