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

    Neuronpedia

    INDEX
    Explanations

    super followed by position, tetrahedron, or gravity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.96
    ا
    0.62
     pollution
    0.61
    و
    0.61
     měl
    0.59
     fable
    0.58
    uana
    0.58
    ‘
    0.58
    این
    0.58
    ка
    0.57
    POSITIVE LOGITS
    rie
    0.68
    submit
    0.61
    ilidade
    0.59
    rei
    0.59
     एस
    0.58
    ing
    0.57
    atine
    0.57
    flo
    0.56
    ie
    0.56
    ્ર
    0.56
    Act Density 0.003%

    No Known Activations