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

    Neuronpedia

    INDEX
    Explanations

    qualities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vibe
    1.32
     kiddos
    1.22
     nochmal
    1.15
     runter
    1.14
     vibes
    1.13
     skincare
    1.11
     upfront
    1.08
    ებისთვის
    1.07
     headspace
    1.06
     synced
    1.05
    POSITIVE LOGITS
     तथा
    0.86
    Although
    0.79
    ;
    0.77
    ¿
    0.73
    although
    0.71
    ;(
    0.71
     Although
    0.67
     (
    0.66
    Adapted
    0.65
    ं
    0.65
    Act Density 0.024%

    No Known Activations