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

    Neuronpedia

    INDEX
    Explanations

    right parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }(
    0.40
    ([
    0.40
     emph
    0.39
    ński
    0.38
     histories
    0.37
    গম
    0.37
    }+(
    0.37
     complexes
    0.37
    existence
    0.36
     generously
    0.36
    POSITIVE LOGITS
    Els
    0.42
    ционно
    0.39
     कानून
    0.39
    檎
    0.39
    ALING
    0.38
    angaroo
    0.38
    OLO
    0.38
     নেতা
    0.38
    الصفحه
    0.38
    ORO
    0.37
    Act Density 0.001%

    No Known Activations