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

    Neuronpedia

    INDEX
    Explanations

    value proposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     C
    0.50
     h
    0.49
     Y
    0.48
    r
    0.47
     Collect
    0.47
     ?",
    0.47
     Road
    0.46
    ram
    0.46
     It
    0.45
     Next
    0.45
    POSITIVE LOGITS
     biomarkers
    0.49
    🟡
    0.47
    额外
    0.46
    渔
    0.46
     protocolos
    0.45
    饿
    0.45
     endpoints
    0.45
     textes
    0.44
     estreno
    0.44
    <unused30>
    0.43
    Act Density 0.002%

    No Known Activations