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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reminder
    -0.07
     __("
    -0.07
    Sent
    -0.07
     biting
    -0.07
     lettuce
    -0.07
    似
    -0.07
    =response
    -0.07
     trai
    -0.07
    >Total
    -0.06
     ranging
    -0.06
    POSITIVE LOGITS
     اصلاح
    0.07
    deque
    0.06
    _vm
    0.06
    ної
    0.06
     Ø
    0.06
    uts
    0.06
    AZ
    0.06
     países
    0.06
    ína
    0.06
     Unified
    0.06
    Act Density 0.018%

    No Known Activations