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

    Neuronpedia

    INDEX
    Explanations

    speed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     江
    -0.07
    �
    -0.07
    -ts
    -0.06
     губ
    -0.06
    规范
    -0.06
    �ng
    -0.06
     explic
    -0.06
     satire
    -0.06
    (game
    -0.06
    辛
    -0.06
    POSITIVE LOGITS
     subjective
    0.07
    voke
    0.06
     DUI
    0.06
    DATE
    0.06
     brave
    0.06
    WithOptions
    0.06
    .Forms
    0.06
    exit
    0.06
    >?
    0.06
    _post
    0.06
    Act Density 0.074%

    No Known Activations