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

    Neuronpedia

    INDEX
    Explanations

    tolerance and acceptance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (props
    -0.07
    .GetKey
    -0.07
    -toast
    -0.07
     workouts
    -0.07
    (settings
    -0.07
    вается
    -0.06
    (Utils
    -0.06
     pricey
    -0.06
    =rand
    -0.06
    _MetaData
    -0.06
    POSITIVE LOGITS
     있고
    0.06
     있다
    0.06
     briefing
    0.06
     پیدا
    0.06
    associ
    0.06
    881
    0.06
    ('');↵
    0.06
     осві
    0.06
    BAB
    0.06
    -volume
    0.05
    Act Density 0.012%

    No Known Activations