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

    Neuronpedia

    INDEX
    Explanations

    here followed by is or are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FIXME
    0.64
     પા
    0.59
    जीर
    0.57
    그리고
    0.57
     Troubleshooting
    0.55
     சுற்று
    0.53
     Ско
    0.53
    仞
    0.53
    ഹ്ലാ
    0.51
     لخ
    0.51
    POSITIVE LOGITS
     are
    1.75
     is
    1.75
     isn
    1.38
     aren
    1.25
     jsou
    1.20
     was
    1.17
     sono
    1.12
     sont
    1.11
     isnt
    1.11
     είναι
    1.10
    Act Density 0.281%

    No Known Activations