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

    Neuronpedia

    INDEX
    Explanations

    python code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stevenson
    -0.08
     favorites
    -0.07
     themselves
    -0.07
    Sorting
    -0.07
     PRINT
    -0.06
     flask
    -0.06
     Sunday
    -0.06
    instance
    -0.06
     nguyện
    -0.06
    osa
    -0.06
    POSITIVE LOGITS
     ngOnDestroy
    0.07
    허
    0.07
    �
    0.07
     xét
    0.07
     월세
    0.07
     Comm
    0.06
    \Events
    0.06
    .…
    0.06
     condi
    0.06
     '<%=
    0.06
    Act Density 0.008%

    No Known Activations