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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bychom
    -0.07
    ourcem
    -0.06
    سمة
    -0.06
     žena
    -0.06
    ystate
    -0.06
    ATTER
    -0.06
     کارت
    -0.06
     Kaw
    -0.06
     başlay
    -0.06
    RODUCTION
    -0.06
    POSITIVE LOGITS
    Primary
    0.07
     záb
    0.06
    ADS
    0.06
    iders
    0.06
    /native
    0.06
    德
    0.06
    .tech
    0.06
    _unit
    0.06
    	num
    0.06
     Lockheed
    0.06
    Act Density 0.000%

    No Known Activations