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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     спіл
    -0.06
    573
    -0.06
     playerName
    -0.06
    �
    -0.06
     Berm
    -0.06
     Köy
    -0.06
     hardcoded
    -0.06
     Karlov
    -0.06
    ufen
    -0.06
    contenido
    -0.06
    POSITIVE LOGITS
     feature
    0.07
    reature
    0.07
    dal
    0.07
    pll
    0.06
     unk
    0.06
     Years
    0.06
    -mode
    0.06
    _primitive
    0.06
     REPORT
    0.06
     medications
    0.06
    Act Density 0.023%

    No Known Activations