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

    Neuronpedia

    INDEX
    Explanations

    technical errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.51
    <bos>
    -0.47
     expands
    -0.43
     مرئيه
    -0.42
     endfor
    -0.42
     nanti
    -0.41
     übers
    -0.41
     bows
    -0.40
     Dolly
    -0.40
     argues
    -0.39
    POSITIVE LOGITS
     विश्वसनीयता
    0.82
    #+#
    0.72
     Preferencias
    0.68
    ReferenceEquals
    0.67
    ArgsConstructor
    0.67
    HomeAsUpEnabled
    0.67
    AntiForgeryToken
    0.65
    CompilerServices
    0.63
    पया
    0.62
    ScopeManager
    0.60
    Act Density 0.012%

    No Known Activations