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

    Neuronpedia

    INDEX
    Explanations

    percentages, weights, you, arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InterfaceLine
    0.47
     불
    0.44
    ായി
    0.43
    蕪
    0.42
    料理
    0.42
    בק
    0.41
    tobago
    0.41
    公子
    0.40
     abhis
    0.40
     문자
    0.40
    POSITIVE LOGITS
    x
    0.51
     actinides
    0.48
    Sigma
    0.47
    ics
    0.47
    deps
    0.45
    ps
    0.43
    yla
    0.43
     grasped
    0.43
    get
    0.43
    da
    0.43
    Act Density 0.018%

    No Known Activations