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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Propagation
    -0.71
     propagation
    -0.68
     propagate
    -0.62
     Propag
    -0.61
     propagating
    -0.60
    modb
    -0.59
     microscopic
    -0.58
    ity
    -0.57
     microscope
    -0.57
     workspace
    -0.56
    POSITIVE LOGITS
     насељу
    0.66
     незавершена
    0.59
     betweenstory
    0.58
    featureID
    0.56
    تقاوى
    0.55
     onItemClick
    0.55
    Chham
    0.54
    󠁴
    0.53
    posedge
    0.52
    Rhestr
    0.51
    Act Density 0.269%

    No Known Activations