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

    Neuronpedia

    INDEX
    Explanations

    xml declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Slot
    0.50
    लेषण
    0.50
    Expire
    0.46
    IFEST
    0.46
    Cpp
    0.45
    Jogo
    0.44
    Ecole
    0.44
    SCHOOL
    0.43
    ளின்
    0.43
    Encript
    0.43
    POSITIVE LOGITS
    es
    0.45
    ু
    0.44
     cốc
    0.43
     Councillor
    0.41
     Bur
    0.41
     XML
    0.40
    u
    0.40
     Elliot
    0.40
     Información
    0.39
     Plate
    0.38
    Act Density 0.000%

    No Known Activations