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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PropertyChanging
    -0.72
    }`).
    -0.71
     Réponses
    -0.68
     EconPapers
    -0.67
    ulink
    -0.67
     HasFactory
    -0.66
    AnchorTagHelper
    -0.66
    StoryboardSegue
    -0.65
     nahilalakip
    -0.65
     createSlice
    -0.65
    POSITIVE LOGITS
     without
    0.50
    Ligações
    0.42
    corsi
    0.39
     unarmed
    0.38
     sans
    0.38
    without
    0.37
     WITHOUT
    0.37
    tront
    0.36
    soever
    0.36
     fără
    0.36
    Act Density 0.013%

    No Known Activations