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

    Neuronpedia

    INDEX
    Explanations

    Hackney, London

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    𬭩
    -0.07
     요청
    -0.07
    .NoError
    -0.07
    brero
    -0.07
    حمد
    -0.07
    大
    -0.07
    .vn
    -0.07
    雲
    -0.07
    frica
    -0.07
    POSITIVE LOGITS
    掌握了
    0.07
     kidnapping
    0.07
     restricting
    0.07
     murdering
    0.06
    -Christian
    0.06
    umping
    0.06
    Checks
    0.06
    Warning
    0.06
     aiding
    0.06
     denying
    0.06
    Act Density 0.002%

    No Known Activations