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

    Neuronpedia

    INDEX
    Explanations

    warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BCE
    -0.07
    erif
    -0.07
    mpi
    -0.06
    cascade
    -0.06
    nych
    -0.06
     HALF
    -0.06
    Neo
    -0.06
    ission
    -0.06
     merges
    -0.06
     Surf
    -0.06
    POSITIVE LOGITS
    до
    0.07
     pinned
    0.07
    ㄷ
    0.06
     vigilant
    0.06
     بي
    0.06
    ाथ
    0.06
    .↵
    0.06
     getMenu
    0.06
     adb
    0.06
    -server
    0.06
    Act Density 0.029%

    No Known Activations