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

    Neuronpedia

    INDEX
    Explanations

    ?>

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Observable
    -0.07
    Code
    -0.07
    Two
    -0.07
    -def
    -0.07
    @Json
    -0.07
     throughout
    -0.07
    installed
    -0.06
     PET
    -0.06
     gram
    -0.06
    properties
    -0.06
    POSITIVE LOGITS
     إليه
    0.07
     Cleaner
    0.06
     شدن
    0.06
     trp
    0.06
     olay
    0.06
    加入
    0.06
    家伙
    0.06
     uống
    0.06
     elektrik
    0.06
     Howard
    0.06
    Act Density 0.004%

    No Known Activations