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

    Neuronpedia

    INDEX
    Explanations

    library paths and collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    له
    0.39
     Merle
    0.38
    otically
    0.37
     Sensitive
    0.37
    لين
    0.36
     Contour
    0.36
    rer
    0.36
     protegido
    0.36
     Surround
    0.36
     surrounds
    0.35
    POSITIVE LOGITS
     LIBRARY
    0.53
    Libraries
    0.52
    блиоте
    0.52
    Library
    0.50
     lib
    0.48
     Libraries
    0.48
    library
    0.48
    LIB
    0.48
    LIBRARY
    0.47
    IBRARY
    0.46
    Act Density 0.005%

    No Known Activations