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

    Neuronpedia

    INDEX
    Explanations

    text and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shil
    0.38
    포츠
    0.37
    નગર
    0.36
    ཤ
    0.35
     Counseling
    0.35
    mapSize
    0.35
     Stru
    0.35
     emulsions
    0.34
     jato
    0.34
    樀
    0.34
    POSITIVE LOGITS
    Ļ
    0.41
    CSE
    0.38
    Clarke
    0.38
    imia
    0.37
    ice
    0.36
     பரி
    0.36
    ics
    0.36
    Clark
    0.36
    nan
    0.36
    Nan
    0.36
    Act Density 0.029%

    No Known Activations