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

    Neuronpedia

    INDEX
    Explanations

    evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     velha
    -0.69
     perfons
    -0.66
    ſelves
    -0.66
     figliu
    -0.65
     démo
    -0.65
     becauſe
    -0.64
     Theſe
    -0.64
     demurrer
    -0.64
     myſelf
    -0.64
    ſelf
    -0.63
    POSITIVE LOGITS
     of
    1.09
    AndEndTag
    0.91
    ValueStyle
    0.71
     GenerationType
    0.66
    PerformLayout
    0.61
    Personendaten
    0.59
    DockStyle
    0.57
     NSCoder
    0.55
    AddTagHelper
    0.54
    kloped
    0.54
    Act Density 0.039%

    No Known Activations