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

    Neuronpedia

    INDEX
    Explanations

    functional descriptions and reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蝈
    0.50
    ChessBot
    0.47
    ennzeichnet
    0.47
     відео
    0.47
    issanti
    0.45
    ção
    0.44
    اته
    0.44
    ieck
    0.44
    狰
    0.44
    chatID
    0.44
    POSITIVE LOGITS
    、
    0.53
     scav
    0.48
     rarely
    0.45
     maintain
    0.45
     re
    0.45
     resist
    0.45
     less
    0.45
     dominate
    0.44
     support
    0.44
     shower
    0.44
    Act Density 0.004%

    No Known Activations