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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inaug
    -0.06
     servlet
    -0.06
     sarcast
    -0.06
     البي
    -0.06
    tons
    -0.06
     bleak
    -0.06
    .setAdapter
    -0.06
    獲得
    -0.06
     chores
    -0.06
     repayment
    -0.06
    POSITIVE LOGITS
    oding
    0.07
     bek
    0.07
    -speed
    0.07
    blems
    0.07
    _kelas
    0.06
     Dutch
    0.06
    God
    0.06
    _dump
    0.06
    ROT
    0.06
    (hash
    0.06
    Act Density 0.013%

    No Known Activations