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

    Neuronpedia

    INDEX
    Explanations

    conference

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rhode
    -0.08
     insanely
    -0.07
     EVE
    -0.07
    드립
    -0.07
    不舍
    -0.07
     unwilling
    -0.07
    �
    -0.07
    _elements
    -0.07
     שאינם
    -0.07
    .@
    -0.07
    POSITIVE LOGITS
     conference
    0.08
     //!
    0.07
    嘛
    0.07
    회사
    0.07
    -court
    0.07
     Frauen
    0.07
    PRINTF
    0.07
    EMON
    0.07
    	String
    0.07
     newspaper
    0.07
    Act Density 0.009%

    No Known Activations