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

    Neuronpedia

    INDEX
    Explanations

    physical descriptions and enclosures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     famously
    0.43
    Month
    0.42
    LastName
    0.42
    Null
    0.41
    Agreement
    0.41
    Nationality
    0.41
    нула
    0.40
    Provenance
    0.40
     elusive
    0.39
     ఇలా
    0.39
    POSITIVE LOGITS
     surrounded
    0.59
     slightly
    0.58
     glows
    0.57
     rotates
    0.56
     ligeramente
    0.56
     puls
    0.55
     tapering
    0.55
     diámetro
    0.55
     flanked
    0.54
     fluores
    0.54
    Act Density 0.018%

    No Known Activations