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

    Neuronpedia

    INDEX
    Explanations

    operate/emitting/heats/plumes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ଝ
    0.83
    ILABLE
    0.81
     Typh
    0.81
    reetype
    0.79
     মধ্য
    0.78
     inclusion
    0.77
     reluctant
    0.76
    Ẵ
    0.74
     Liter
    0.74
    incing
    0.74
    POSITIVE LOGITS
    accia
    0.78
    contact
    0.73
    Abstract
    0.69
    esta
    0.68
    compare
    0.66
    ##
    0.65
    abstract
    0.63
    நாம்
    0.62
     Abstract
    0.61
    fe
    0.61
    Act Density 0.000%

    No Known Activations