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

    Neuronpedia

    INDEX
    Explanations

    indexed variables in math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     studios
    -0.09
     Superman
    -0.08
     Guardians
    -0.07
     tranh
    -0.07
     prática
    -0.07
     studio
    -0.07
     práctica
    -0.07
     reopening
    -0.07
     hipó
    -0.07
     Jee
    -0.07
    POSITIVE LOGITS
     sis
    0.08
     seh
    0.08
     countdown
    0.08
     Desert
    0.08
    left
    0.08
     liwat
    0.08
    @Column
    0.08
     каталог
    0.08
    הילה
    0.08
     ultime
    0.08
    Act Density 0.007%

    No Known Activations