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

    Neuronpedia

    INDEX
    Explanations

    edit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orne
    -0.08
    nde
    -0.07
    說話
    -0.07
    按钮
    -0.07
     dresser
    -0.07
    .DataPropertyName
    -0.07
     группы
    -0.07
    (dep
    -0.06
    pository
    -0.06
    コミュニケ
    -0.06
    POSITIVE LOGITS
     arttır
    0.08
     adds
    0.07
    东路
    0.07
    ])==
    0.07
     facilitate
    0.07
    밈
    0.07
    _FWD
    0.07
    бин
    0.07
    .Step
    0.06
    (mat
    0.06
    Act Density 0.005%

    No Known Activations