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

    Neuronpedia

    INDEX
    Explanations

    describes how things are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RELAND
    0.41
     daugiau
    0.39
     fast
    0.38
     Mayor
    0.38
     Cheval
    0.38
     Ro
    0.37
     lads
    0.37
    issez
    0.37
     Deux
    0.37
     बटे
    0.37
    POSITIVE LOGITS
     وضاحت
    0.46
     క్రి
    0.41
    covered
    0.40
    akkhati
    0.39
    sulfonyl
    0.39
    முருக
    0.39
    ilj
    0.38
     subordination
    0.38
     sutures
    0.37
     దృష్టి
    0.37
    Act Density 0.001%

    No Known Activations