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

    Neuronpedia

    INDEX
    Explanations

    incidence rate calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.50
     pesticide
    0.43
    sim
    0.42
     indefinitely
    0.42
    generic
    0.42
     Player
    0.41
    mix
    0.41
    벙
    0.41
    right
    0.40
    dim
    0.40
    POSITIVE LOGITS
     organização
    0.47
    ebabkan
    0.46
     alterações
    0.46
    احث
    0.46
     Código
    0.45
    胛
    0.45
     جوړونکو
    0.45
    巖
    0.44
     chamada
    0.44
     hals
    0.44
    Act Density 0.001%

    No Known Activations