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

    Neuronpedia

    INDEX
    Explanations

    stages of disease/topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     production
    -0.87
    production
    -0.80
    Production
    -0.68
     Production
    -0.65
     productions
    -0.63
     PRODUCTION
    -0.60
    PRODUCTION
    -0.53
     produção
    -0.52
    pool
    -0.51
    stage
    -0.51
    POSITIVE LOGITS
    zzleHttp
    1.02
     autorytatywna
    0.92
     GenerationType
    0.84
    躇
    0.84
     estekak
    0.84
     الحره
    0.83
     سكانية
    0.78
    LLocation
    0.76
    InjectAttribute
    0.74
    #+#
    0.74
    Act Density 0.099%

    No Known Activations