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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rip
    -0.06
    bes
    -0.06
     fortn
    -0.06
     LayoutInflater
    -0.06
    .department
    -0.06
     hadn
    -0.06
    .Environment
    -0.06
    _fmt
    -0.06
    -ver
    -0.06
    名前
    -0.06
    POSITIVE LOGITS
     privileges
    0.07
    Thank
    0.07
     δημιουργ
    0.07
     NOR
    0.06
    respons
    0.06
     ประก
    0.06
    GRID
    0.06
     TRY
    0.06
    portion
    0.06
     Rach
    0.06
    Act Density 0.002%

    No Known Activations