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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     若
    -0.07
    若
    -0.06
     buscar
    -0.06
    ה
    -0.06
     Covenant
    -0.06
     الذهاب
    -0.06
    щают
    -0.06
     abrir
    -0.06
     pä
    -0.06
    Sid
    -0.06
    POSITIVE LOGITS
     DeV
    0.07
    :type
    0.06
     MARK
    0.06
    	import
    0.06
    .jasper
    0.06
     hate
    0.06
     laughed
    0.06
    /system
    0.06
     amd
    0.06
     propagate
    0.06
    Act Density 0.013%

    No Known Activations