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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    control
    -0.07
     orden
    -0.07
    -weight
    -0.07
     conquer
    -0.06
    _splits
    -0.06
    ivos
    -0.06
    Apellido
    -0.06
     vigil
    -0.06
    oven
    -0.06
    -radio
    -0.06
    POSITIVE LOGITS
    .createdAt
    0.06
    .listBox
    0.06
    殊
    0.06
     XCT
    0.06
    ün
    0.06
    !");↵
    0.06
     生命周期
    0.06
     Craw
    0.06
    σον
    0.06
    ]")]↵
    0.06
    Act Density 0.009%

    No Known Activations