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

    Neuronpedia

    INDEX
    Explanations

    Hashtags

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     timers
    -0.07
     ki
    -0.06
     cree
    -0.06
    mouseover
    -0.06
     knees
    -0.06
    _LOC
    -0.06
     Apostle
    -0.06
    Files
    -0.06
     preserved
    -0.06
     drained
    -0.06
    POSITIVE LOGITS
    -get
    0.07
    "..
    0.07
    _render
    0.07
    ."
    0.06
     інш
    0.06
    _numero
    0.06
     จำนวน
    0.06
     рождения
    0.06
    "][
    0.06
    ;};↵
    0.06
    Act Density 0.041%

    No Known Activations