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

    Neuronpedia

    INDEX
    Explanations

    say "prior"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一一
    -0.08
     Kaiser
    -0.08
     Anne
    -0.08
    TRY
    -0.07
     Hag
    -0.07
    暨
    -0.07
     JO
    -0.07
    Uses
    -0.07
     hace
    -0.07
     Ain
    -0.07
    POSITIVE LOGITS
    عائل
    0.07
    系统的
    0.07
    reb
    0.07
     superintendent
    0.06
    ：↵
    0.06
    upported
    0.06
    ometric
    0.06
    ��드
    0.06
    قب
    0.06
     NI
    0.06
    Act Density 0.001%

    No Known Activations