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

    Neuronpedia

    INDEX
    Explanations

    macOS integration offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Swift
    0.51
    أي
    0.49
    溫
    0.47
    MARK
    0.45
     Tân
    0.44
    Diện
    0.44
     أو
    0.43
    如
    0.43
    ivity
    0.43
    CCION
    0.43
    POSITIVE LOGITS
     usefulness
    0.47
    waukee
    0.47
     stabil
    0.47
     caus
    0.46
    forestation
    0.46
     rumin
    0.46
     smells
    0.45
     kinda
    0.45
     cravings
    0.45
     maybe
    0.45
    Act Density 0.000%

    No Known Activations