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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -1.05
    rawDesc
    -0.82
    gnore
    -0.73
    toggler
    -0.71
    IsMutable
    -0.69
    Personendaten
    -0.68
    athen
    -0.66
     <=",
    -0.65
    Obrázky
    -0.64
    gusting
    -0.63
    POSITIVE LOGITS
     démocr
    0.67
     cotone
    0.58
     dieux
    0.57
     âmes
    0.54
     chré
    0.54
     avoient
    0.54
     coppia
    0.53
     hjälp
    0.52
     traités
    0.51
     hjälpa
    0.51
    Act Density 0.091%

    No Known Activations