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

    Neuronpedia

    INDEX
    Explanations

    Code/equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Marks
    -0.07
    ้เป
    -0.07
    (track
    -0.07
     kter
    -0.07
     несколько
    -0.07
     motives
    -0.06
    geç
    -0.06
     klíč
    -0.06
    NSNotification
    -0.06
    기관
    -0.06
    POSITIVE LOGITS
    %.↵
    0.07
    254
    0.06
    (logging
    0.06
    จ
    0.06
     gymn
    0.06
    olf
    0.06
     Burton
    0.06
    lou
    0.06
     ↵
    0.06
    quarters
    0.06
    Act Density 0.002%

    No Known Activations