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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     相
    -0.07
     hjem
    -0.07
    相
    -0.07
     restriction
    -0.06
     resilient
    -0.06
     setter
    -0.06
     konce
    -0.06
     osob
    -0.06
    Israel
    -0.06
     rebel
    -0.06
    POSITIVE LOGITS
     پس
    0.06
     สพป
    0.06
    ↵	
↵
    0.06
     loại
    0.06
    ุค
    0.06
    /ss
    0.06
     incorrect
    0.06
    _ORD
    0.06
    (jButton
    0.06
    fontWeight
    0.06
    Act Density 0.004%

    No Known Activations