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

    Neuronpedia

    INDEX
    Explanations

    score

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maya
    -0.07
    kw
    -0.07
     mama
    -0.06
     має
    -0.06
    ią
    -0.06
    Reservation
    -0.06
    QC
    -0.06
    柄
    -0.06
    ?,?,?,?,
    -0.06
    _voice
    -0.06
    POSITIVE LOGITS
    /render
    0.07
     cient
    0.06
    _ALIGNMENT
    0.06
     GOP
    0.06
     discount
    0.06
     συμβ
    0.06
     tup
    0.06
    _DOT
    0.06
    charge
    0.06
     GmbH
    0.06
    Act Density 0.015%

    No Known Activations