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

    Neuronpedia

    INDEX
    Explanations

    Game rules involving numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     സർ
    -0.08
     avo
    -0.07
     Industries
    -0.07
     fud
    -0.07
     ഭ
    -0.07
     deo
    -0.07
     सर
    -0.07
     Big
    -0.07
    िक
    -0.07
     باد
    -0.07
    POSITIVE LOGITS
    瞬
    0.12
     sooner
    0.11
     순간
    0.11
     instantaneous
    0.10
     Shortly
    0.09
     cease
    0.09
    Reached
    0.09
     sometime
    0.09
     milestones
    0.09
    queen
    0.09
    Act Density 0.018%

    No Known Activations