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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лені
    -0.07
     Mug
    -0.07
    acus
    -0.07
    wner
    -0.06
    ''
    -0.06
    _KEYWORD
    -0.06
    ediği
    -0.06
     virus
    -0.06
     Medi
    -0.06
    condition
    -0.06
    POSITIVE LOGITS
     consultation
    0.07
     electrode
    0.07
    站在
    0.07
     scrapped
    0.07
     Disneyland
    0.07
    	delay
    0.07
     expiration
    0.06
     quartz
    0.06
     observing
    0.06
     album
    0.06
    Act Density 0.045%

    No Known Activations