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

    Neuronpedia

    INDEX
    Explanations

    single location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뮹
    -0.07
    orie
    -0.07
    قوا
    -0.07
    فين
    -0.07
    orman
    -0.07
     Bord
    -0.07
    Zone
    -0.06
    파
    -0.06
    ovich
    -0.06
    痱
    -0.06
    POSITIVE LOGITS
     sweetness
    0.07
    ◠
    0.07
    weeks
    0.07
    chos
    0.07
     As
    0.07
    ✕
    0.07
    (Menu
    0.07
    $rows
    0.07
     بلد
    0.07
     société
    0.07
    Act Density 0.053%

    No Known Activations