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

    Neuronpedia

    INDEX
    Explanations

    typ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     démocr
    -0.65
     prêtres
    -0.65
     varandra
    -0.56
     almohada
    -0.55
     hög
    -0.55
     supérieurs
    -0.55
     prisonniers
    -0.54
     économiques
    -0.54
     högre
    -0.53
     vägen
    -0.53
    POSITIVE LOGITS
    DockStyle
    0.89
     للمعارف
    0.85
    rungsseite
    0.84
    tagHelperRunner
    0.84
     Италијани
    0.82
     betweenstory
    0.79
    NameInMap
    0.79
    expandindo
    0.79
     Administrativna
    0.78
    InjectAttribute
    0.77
    Act Density 0.002%

    No Known Activations