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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rulers
    -0.07
    532
    -0.07
     Accept
    -0.06
     colonial
    -0.06
    립니다
    -0.06
    提供
    -0.06
    prenom
    -0.06
    ény
    -0.06
     пло
    -0.06
     exceeds
    -0.06
    POSITIVE LOGITS
     Barb
    0.07
    .pb
    0.06
    ASY
    0.06
     reinforcements
    0.06
    .retry
    0.06
     تفس
    0.06
     alcuni
    0.06
     Tart
    0.06
    TX
    0.06
     سو
    0.06
    Act Density 0.002%

    No Known Activations