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

    Neuronpedia

    INDEX
    Explanations

    support services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ji
    0.61
    jali
    0.55
    ad
    0.55
    hi
    0.53
    sis
    0.51
    lla
    0.50
    вых
    0.50
    ،
    0.50
    ho
    0.50
    no
    0.49
    POSITIVE LOGITS
     நாடுகளில்
    0.62
     concerts
    0.59
     abusers
    0.59
     crianças
    0.57
     Tahun
    0.57
     campaigners
    0.57
     calves
    0.57
     órgãos
    0.57
     مراکز
    0.57
     koncert
    0.56
    Act Density 0.122%

    No Known Activations