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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confirms
    -0.07
    frame
    -0.07
    ộc
    -0.06
     기간
    -0.06
     البد
    -0.06
     biến
    -0.06
     adım
    -0.06
     scoreboard
    -0.06
     rend
    -0.06
    Put
    -0.06
    POSITIVE LOGITS
    (extra
    0.07
    _Texture
    0.06
    _embedding
    0.06
     understanding
    0.06
    cloak
    0.06
    EmailAddress
    0.06
     oversized
    0.06
     Understand
    0.06
    SceneManager
    0.06
    hpp
    0.06
    Act Density 0.000%

    No Known Activations