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

    Neuronpedia

    INDEX
    Explanations

    old or told (detects storytelling or age)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    赶
    -0.07
     Markup
    -0.07
     DIFF
    -0.07
     parfait
    -0.06
    _RGBA
    -0.06
     suscept
    -0.06
     Darren
    -0.06
     فکی
    -0.06
    .erb
    -0.06
     datasets
    -0.06
    POSITIVE LOGITS
    NSS
    0.07
    OLD
    0.06
    tw
    0.06
     sel
    0.06
    unc
    0.06
     wonder
    0.06
     asked
    0.06
    arse
    0.06
     nông
    0.06
     coconut
    0.06
    Act Density 0.007%

    No Known Activations