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

    Neuronpedia

    INDEX
    Explanations

    units of measure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sad
    0.45
     resin
    0.45
     successors
    0.44
    m
    0.40
     buys
    0.39
     toys
    0.38
     fashioned
    0.38
     bottles
    0.37
     gages
    0.37
     handy
    0.37
    POSITIVE LOGITS
    𝓵
    0.56
     ???
    0.48
     बाधा
    0.46
     ajustar
    0.44
     REGIUNI
    0.43
     بينهم
    0.43
     editar
    0.43
    uclease
    0.43
     "|
    0.42
     OCPP
    0.42
    Act Density 0.001%

    No Known Activations