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

    Neuronpedia

    INDEX
    Explanations

    story beginnings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cartel
    -0.07
    Ł
    -0.07
     anak
    -0.07
    靠着
    -0.06
    滿
    -0.06
    接连
    -0.06
     wł
    -0.06
    ird
    -0.06
    忧虑
    -0.06
    Isl
    -0.06
    POSITIVE LOGITS
    $fdata
    0.07
     Tribute
    0.07
    .Release
    0.07
     sublime
    0.07
     sophomore
    0.06
    心情
    0.06
    شرف
    0.06
     Midi
    0.06
    محا
    0.06
     السلام
    0.06
    Act Density 0.195%

    No Known Activations