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

    Neuronpedia

    INDEX
    Explanations

    Civil Service

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     konuşma
    -0.08
     Rookie
    -0.07
    连锁
    -0.07
     Pluto
    -0.07
     המכ
    -0.07
    spiel
    -0.07
    radio
    -0.07
    禅
    -0.07
    荃
    -0.06
     Cave
    -0.06
    POSITIVE LOGITS
     Article
    0.07
    _locs
    0.07
    ڊ
    0.07
    (ind
    0.07
     societies
    0.07
    Destination
    0.07
    Unc
    0.07
     originated
    0.07
    _patches
    0.07
     yPos
    0.07
    Act Density 0.019%

    No Known Activations