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

    Neuronpedia

    INDEX
    Explanations

    suggesting or indicating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acclaim
    1.45
     innovators
    1.25
     customers
    1.23
     ideology
    1.17
     slats
    1.15
     accolades
    1.14
    逖
    1.13
     automakers
    1.13
    ین
    1.12
    زين
    1.12
    POSITIVE LOGITS
    eurs
    1.18
    TS
    1.13
    ments
    1.06
    te
    1.05
     şekilde
    1.02
     некоторое
    1.02
     nämlich
    1.02
    up
    0.97
    iz
    0.96
    AL
    0.95
    Act Density 0.119%

    No Known Activations