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

    Neuronpedia

    INDEX
    Explanations

    coding questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    th
    -0.07
     Suz
    -0.07
     पद
    -0.07
    .mon
    -0.07
     خلق
    -0.06
    getBlock
    -0.06
     الوز
    -0.06
    .uniform
    -0.06
     Survivor
    -0.06
     ****************************************************************
    -0.06
    POSITIVE LOGITS
     defined
    0.08
     conclude
    0.06
     supposedly
    0.06
     Defined
    0.06
     connecting
    0.06
     cooked
    0.06
    ��
    0.06
     knocked
    0.06
    genome
    0.06
    etin
    0.06
    Act Density 0.013%

    No Known Activations