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

    Neuronpedia

    INDEX
    Explanations

    rare occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    窟
    0.36
     many
    0.35
     {
    0.35
    െടുത്തു
    0.35
    many
    0.35
     Many
    0.34
     Lauderdale
    0.34
    ⓛ
    0.34
     adjusted
    0.34
     liberals
    0.34
    POSITIVE LOGITS
     rare
    2.94
    Rare
    2.64
     Rare
    2.63
    rare
    2.50
     rarer
    2.38
     raro
    2.36
     rares
    2.25
     rara
    2.23
     rarity
    2.16
     दुर्लभ
    2.13
    Act Density 0.127%

    No Known Activations