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

    Neuronpedia

    INDEX
    Explanations

    programming and technical subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hoping
    0.55
     compartió
    0.55
     lancement
    0.53
     বাকি
    0.53
     launched
    0.52
    Meanwhile
    0.52
     sementara
    0.52
    DIRECT
    0.51
    launched
    0.51
    Ret
    0.50
    POSITIVE LOGITS
     ofta
    0.73
     brukes
    0.71
    awsze
    0.70
     არის
    0.67
     alltid
    0.66
     contexts
    0.65
    avacanam
    0.65
     används
    0.64
     نیست
    0.62
     является
    0.61
    Act Density 0.019%

    No Known Activations