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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thuốc
    -0.07
     aston
    -0.06
    premium
    -0.06
    	stop
    -0.06
    	explicit
    -0.06
     Fi
    -0.06
    Identity
    -0.06
    248
    -0.06
    ImageButton
    -0.06
    _HELPER
    -0.06
    POSITIVE LOGITS
     jou
    0.07
    real
    0.06
    metro
    0.06
    альну
    0.06
    licated
    0.06
     ];
    0.06
     REAL
    0.06
    rollo
    0.06
     mine
    0.06
     programma
    0.06
    Act Density 0.002%

    No Known Activations