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

    Neuronpedia

    INDEX
    Explanations

    Word problems/riddles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "="
    -0.06
     professor
    -0.06
    会
    -0.06
    "A
    -0.06
    Await
    -0.06
    DESCRIPTION
    -0.06
     guilty
    -0.06
    [to
    -0.06
    ん
    -0.06
     guarded
    -0.06
    POSITIVE LOGITS
     debugger
    0.07
    libs
    0.07
    wat
    0.06
     -----
    0.06
    _CONFIG
    0.06
     buna
    0.06
     목소
    0.06
    }<
    0.06
     учеб
    0.06
     rotation
    0.06
    Act Density 0.039%

    No Known Activations