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

    Neuronpedia

    INDEX
    Explanations

    &&

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aerial
    -0.06
    voke
    -0.06
    メージ
    -0.06
     mantle
    -0.06
     Mk
    -0.06
     seeker
    -0.06
    )↵↵↵↵↵↵
    -0.06
    -the
    -0.06
    uhe
    -0.06
    醴醴
    -0.06
    POSITIVE LOGITS
     vitamin
    0.08
     rotates
    0.07
     declares
    0.06
    ",(
    0.06
     Sophie
    0.06
    .Relative
    0.06
     $(
    0.06
     وقد
    0.06
     就
    0.06
    pressive
    0.06
    Act Density 0.002%

    No Known Activations