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

    Neuronpedia

    INDEX
    Explanations

    relating or linking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    assign
    -0.73
    JspWriter
    -0.73
    بوابة
    -0.70
     aligns
    -0.68
    Personendaten
    -0.68
     aligning
    -0.66
     corresponded
    -0.64
     anhydrous
    -0.64
    帖最后由
    -0.64
    culosis
    -0.63
    POSITIVE LOGITS
     itſelf
    0.93
     himſelf
    0.85
     myſelf
    0.85
     themſelves
    0.82
    leſs
    0.77
    ſelf
    0.72
     purpoſe
    0.72
     ſta
    0.70
    ſelves
    0.68
     perſ
    0.65
    Act Density 0.141%

    No Known Activations