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

    Neuronpedia

    INDEX
    Explanations

    event dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mundo
    -0.07
    Bus
    -0.07
     crit
    -0.06
     листь
    -0.06
     Harvest
    -0.06
     GetName
    -0.06
    ?”↵↵
    -0.06
     FETCH
    -0.06
     pets
    -0.06
     Merry
    -0.06
    POSITIVE LOGITS
     Tradition
    0.06
     unrestricted
    0.06
    mil
    0.06
    	file
    0.06
     знову
    0.06
     отк
    0.06
    acas
    0.06
     referencing
    0.06
     homicides
    0.06
    .textColor
    0.06
    Act Density 0.025%

    No Known Activations