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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COMP
    -0.07
    opsis
    -0.07
    COMP
    -0.07
    /tr
    -0.07
    list
    -0.07
    LIST
    -0.07
     Flash
    -0.07
    "}>↵
    -0.07
     clearance
    -0.06
    CN
    -0.06
    POSITIVE LOGITS
     spoil
    0.07
     vardı
    0.07
     çalışmalar
    0.07
    <thead
    0.06
     والن
    0.06
    _bi
    0.06
    いや
    0.06
     愛
    0.06
    эф
    0.06
     елем
    0.06
    Act Density 0.032%

    No Known Activations