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

    Neuronpedia

    INDEX
    Explanations

    categorized lists and breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     primate
    0.81
     ไอ้
    0.76
     गारंटर
    0.75
    StartPreview
    0.74
    béco
    0.74
     tanggung
    0.74
    ورٹی
    0.72
     zweiten
    0.72
    Prema
    0.72
     ostrich
    0.71
    POSITIVE LOGITS
    SECTION
    0.71
     SECTION
    0.68
     Limitation
    0.66
     ♥
    0.65
     LINKS
    0.65
     COURSE
    0.65
     Google
    0.64
     USER
    0.64
     LIMIT
    0.63
    agd
    0.63
    Act Density 0.044%

    No Known Activations