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

    Neuronpedia

    INDEX
    Explanations

    X versus Y comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    1.34
    -
    1.34
    _
    1.22
    '
    1.17
    ic
    1.16
    fulness
    1.07
    .
    1.07
    entimes
    1.01
    as
    1.01
    "
    1.00
    POSITIVE LOGITS
     teclado
    1.09
     higiene
    1.09
     micrófono
    1.06
     teléfono
    1.05
     kimia
    1.05
     asesinato
    1.04
     conducir
    1.02
     altro
    1.01
     meeste
    1.01
     toplum
    1.01
    Act Density 0.018%

    No Known Activations