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

    Neuronpedia

    INDEX
    Explanations

    "right now" or "now" followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.46
    ay
    1.27
     Arias
    1.19
    an
    1.14
     是
    1.14
     vois
    1.14
     Abbiamo
    1.14
     have
    1.13
     Kend
    1.13
     наличие
    1.13
    POSITIVE LOGITS
    öh
    1.21
    म
    1.16
    ört
    1.15
    ри
    1.13
    zü
    1.08
    .}$
    1.05
    ير
    1.04
    از
    1.01
    öz
    0.99
    ید
    0.98
    Act Density 0.012%

    No Known Activations