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

    Neuronpedia

    INDEX
    Explanations

    parsing non-English symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     တော့
    0.77
    濰
    0.76
    комо
    0.76
     Schutz
    0.72
    তুন
    0.69
     gaming
    0.68
     rasgos
    0.68
     Funktions
    0.68
     maxit
    0.68
     Maroon
    0.67
    POSITIVE LOGITS
    नपुर
    0.67
     Nội
    0.66
    rogate
    0.65
    ².
    0.63
     justify
    0.62
     ജൂ
    0.62
    ต่ำ
    0.61
    ര്‍ച്ച
    0.60
     সামনের
    0.60
    ర్గ
    0.59
    Act Density 0.010%

    No Known Activations