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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tradi
    -0.07
     datastore
    -0.07
     Certif
    -0.07
    调查
    -0.06
     tox
    -0.06
     snack
    -0.06
     keypad
    -0.06
    ARI
    -0.06
     введ
    -0.06
    	full
    -0.06
    POSITIVE LOGITS
    う
    0.08
    VENT
    0.07
     속
    0.07
    ινε
    0.06
     entityManager
    0.06
    '}
    0.06
    /wp
    0.06
    ouncer
    0.06
    สร
    0.06
    /react
    0.06
    Act Density 0.014%

    No Known Activations