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

    Neuronpedia

    INDEX
    Explanations

    book and concept titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recette
    0.22
     INTERNATIONAL
    0.21
     eup
    0.21
     Category
    0.21
     Anfang
    0.20
     programme
    0.20
     raced
    0.20
     विज्ञापन
    0.20
     infographic
    0.20
    栤
    0.20
    POSITIVE LOGITS
    to
    0.28
    ina
    0.24
    allowing
    0.24
    öl
    0.23
    áce
    0.23
    ados
    0.22
    aden
    0.22
    us
    0.22
    yside
    0.21
    ândia
    0.21
    Act Density 0.000%

    No Known Activations