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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ddit
    -0.07
    ROLL
    -0.07
    itals
    -0.07
    原始
    -0.07
    714
    -0.07
    odings
    -0.07
    rops
    -0.07
    oded
    -0.06
    かって
    -0.06
     blinds
    -0.06
    POSITIVE LOGITS
     Tra
    0.07
     стак
    0.07
     kabul
    0.07
     fontsize
    0.06
    =".
    0.06
     poplat
    0.06
     вико
    0.06
     Cumhur
    0.06
     refr
    0.06
    leitung
    0.06
    Act Density 0.016%

    No Known Activations