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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icipants
    -0.07
     semaphore
    -0.07
    [n
    -0.07
     fertilizer
    -0.07
     caller
    -0.07
    eacher
    -0.06
    다가
    -0.06
    feito
    -0.06
    ादन
    -0.06
     AC
    -0.06
    POSITIVE LOGITS
    acağı
    0.07
     UL
    0.06
    DK
    0.06
     deque
    0.06
    ῦ
    0.06
     โ
    0.06
    /*******************************************************************************↵
    0.06
     Наг
    0.06
    OTOS
    0.06
     Pour
    0.06
    Act Density 0.004%

    No Known Activations