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

    Neuronpedia

    INDEX
    Explanations

    SMS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JB
    -0.06
     hierarchical
    -0.06
     hintText
    -0.06
    xBB
    -0.06
    فاق
    -0.06
     Beyond
    -0.06
     Exact
    -0.06
    \Framework
    -0.06
     الی
    -0.06
    ataset
    -0.06
    POSITIVE LOGITS
    万円
    0.07
    Participant
    0.07
    rod
    0.06
    acích
    0.06
    なんて
    0.06
    smart
    0.06
     zákaz
    0.06
     гри
    0.06
    @RestController
    0.06
    afen
    0.06
    Act Density 0.438%

    No Known Activations