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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ε
    -0.07
     driveway
    -0.07
    ają
    -0.07
     IBM
    -0.06
    .imwrite
    -0.06
    .@
    -0.06
    uhe
    -0.06
     initiator
    -0.06
    ющими
    -0.06
    suspend
    -0.06
    POSITIVE LOGITS
     законодатель
    0.07
     тка
    0.07
     літ
    0.07
     çap
    0.06
     disadvantaged
    0.06
    市场
    0.06
    /^
    0.06
     incompet
    0.06
     الو
    0.06
     excess
    0.06
    Act Density 0.043%

    No Known Activations