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

    Neuronpedia

    INDEX
    Explanations

    offer support and balance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ERO
    0.51
     reconocida
    0.48
    IB
    0.48
    IAN
    0.47
     cierto
    0.47
     operadores
    0.47
     cierta
    0.47
     caterpillar
    0.47
     увели
    0.46
    ේ
    0.46
    POSITIVE LOGITS
    rescences
    0.47
    swarm
    0.46
     ethnographic
    0.43
    hesize
    0.43
     longterm
    0.43
     Underlying
    0.43
    hort
    0.42
     morphological
    0.41
    店铺
    0.41
    ся
    0.41
    Act Density 0.001%

    No Known Activations