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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pounds
    -0.07
    oundary
    -0.06
     vital
    -0.06
    vic
    -0.06
    omnia
    -0.06
    return
    -0.06
    στό
    -0.06
     varchar
    -0.06
    095
    -0.06
     bureau
    -0.06
    POSITIVE LOGITS
    Sexy
    0.07
    사랑
    0.06
    خرید
    0.06
     Bone
    0.06
     noveller
    0.06
    PyObject
    0.06
    Bone
    0.06
    やる夫
    0.06
     compromises
    0.06
    mount
    0.06
    Act Density 0.232%

    No Known Activations