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

    Neuronpedia

    INDEX
    Explanations

    say "ed"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NEAR
    -0.06
    ≤
    -0.06
     Catalyst
    -0.06
     triangle
    -0.06
     万円
    -0.06
     Ig
    -0.06
     다양한
    -0.06
     Nur
    -0.06
     Aug
    -0.06
    _Level
    -0.06
    POSITIVE LOGITS
    WAY
    0.08
    DX
    0.07
    ết
    0.06
    way
    0.06
     blooms
    0.06
     prem
    0.06
     CHAPTER
    0.06
     assured
    0.06
     sleep
    0.06
     extends
    0.06
    Act Density 0.002%

    No Known Activations