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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shoved
    -0.06
    And
    -0.06
    ΟΔ
    -0.06
     KT
    -0.06
     War
    -0.06
     ROI
    -0.06
    亞
    -0.06
    SetText
    -0.06
     have
    -0.06
    .permission
    -0.06
    POSITIVE LOGITS
    .Weight
    0.07
    èle
    0.07
     Supports
    0.06
    _called
    0.06
    к
    0.06
     จาก
    0.06
     stal
    0.06
    !)
    0.06
    Rib
    0.06
    из
    0.06
    Act Density 0.068%

    No Known Activations