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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    相伴
    -0.08
    leDb
    -0.07
     slowly
    -0.07
    PDF
    -0.07
     göz
    -0.06
     저장
    -0.06
    审理
    -0.06
     طفل
    -0.06
     predator
    -0.06
    を探
    -0.06
    POSITIVE LOGITS
     Gü
    0.08
    戈
    0.07
     Wagner
    0.07
    ګ
    0.07
     Maria
    0.07
    (Mod
    0.07
     Tango
    0.07
    ogle
    0.06
     vou
    0.06
    nyder
    0.06
    Act Density 0.113%

    No Known Activations