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

    Neuronpedia

    INDEX
    Explanations

    lists of categories and qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elektromagnet
    0.41
     glucocortic
    0.39
    gebras
    0.37
    <h2>
    0.37
    lardır
    0.36
     qubits
    0.36
    мыми
    0.35
     symmetries
    0.34
    manifolds
    0.34
     stderr
    0.34
    POSITIVE LOGITS
     P
    0.43
     R
    0.41
     B
    0.41
    ing
    0.40
     Service
    0.40
    ة
    0.39
     T
    0.39
     Th
    0.38
     Day
    0.38
     L
    0.38
    Act Density 0.113%

    No Known Activations