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

    Neuronpedia

    INDEX
    Explanations

    undercover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    specs
    -0.07
     Dialogue
    -0.06
     Fil
    -0.06
     Magnus
    -0.06
    líž
    -0.06
     Glas
    -0.06
    paging
    -0.06
     النظام
    -0.06
     Fade
    -0.06
     '\\'
    -0.06
    POSITIVE LOGITS
     undercover
    0.12
     covert
    0.08
     clandest
    0.08
     overclock
    0.07
    ateurs
    0.07
    в
    0.07
    пня
    0.07
    ！」↵↵
    0.06
    escort
    0.06
     disguise
    0.06
    Act Density 0.001%

    No Known Activations