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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mLocation
    0.52
    ací
    0.49
    فيه
    0.49
     Signup
    0.48
    Municipio
    0.47
    리소스
    0.47
    dach
    0.46
    Toc
    0.45
    تقديم
    0.45
     élevé
    0.45
    POSITIVE LOGITS
    s
    0.61
     skyscrapers
    0.59
     ампли
    0.57
    ாதீர்கள்
    0.54
    ς
    0.52
     idealized
    0.52
     спра
    0.51
    ieson
    0.50
     अध्या
    0.50
     бур
    0.50
    Act Density 0.000%

    No Known Activations