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

    Neuronpedia

    INDEX
    Explanations

    Recipes/ingredients lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ư
    -0.06
    _baseline
    -0.06
     sales
    -0.06
    極
    -0.06
     excit
    -0.06
    得
    -0.06
     SOLUTION
    -0.06
     potions
    -0.06
    _box
    -0.06
    Precision
    -0.06
    POSITIVE LOGITS
     smě
    0.07
    ";}↵
    0.06
     stol
    0.06
     leben
    0.06
    sock
    0.06
    ordering
    0.06
     "|"
    0.06
    .wr
    0.06
     encoded
    0.06
    -----------↵
    0.06
    Act Density 0.047%

    No Known Activations