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

    Neuronpedia

    INDEX
    Explanations

    orientation/angles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     linh
    -0.07
     monopoly
    -0.06
    fé
    -0.06
     Сред
    -0.06
    lendirme
    -0.06
     nominations
    -0.06
    -lock
    -0.06
     собою
    -0.06
     Ov
    -0.06
    textarea
    -0.06
    POSITIVE LOGITS
    _por
    0.08
     وضعیت
    0.07
     vyz
    0.06
     serge
    0.06
     стан
    0.06
    �试
    0.06
    URITY
    0.06
    _dirty
    0.06
     nad
    0.06
     gemacht
    0.06
    Act Density 0.172%

    No Known Activations