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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     altercation
    -0.07
     bubbles
    -0.06
    IF
    -0.06
     밝
    -0.06
    (R
    -0.06
    gf
    -0.06
     preferredStyle
    -0.06
    ной
    -0.06
     lt
    -0.06
     &)
    -0.06
    POSITIVE LOGITS
     رسم
    0.07
     Gates
    0.07
     mỹ
    0.07
    ribly
    0.06
     startActivityForResult
    0.06
    .event
    0.06
    feit
    0.06
     XV
    0.06
    機
    0.06
     Gluten
    0.06
    Act Density 0.023%

    No Known Activations