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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     अलग
    -0.07
    階
    -0.06
     vydání
    -0.06
    ")]
↵
    -0.06
    chin
    -0.06
    '}}
    -0.06
    Hero
    -0.06
    ↵				↵
    -0.06
    ，对
    -0.06
    !,↵
    -0.06
    POSITIVE LOGITS
     delightful
    0.07
    oriously
    0.06
     equip
    0.06
    kwargs
    0.06
     Porn
    0.06
    :::::::::::
    0.06
     rights
    0.06
    tridge
    0.06
    turned
    0.06
     unlawful
    0.06
    Act Density 0.004%

    No Known Activations