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

    Neuronpedia

    INDEX
    Explanations

    meta charset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sí
    0.59
    hér
    0.57
    manifolds
    0.55
    ج
    0.55
    li
    0.55
    hoc
    0.55
    administration
    0.54
    ut
    0.54
    personas
    0.54
    gah
    0.54
    POSITIVE LOGITS
    />
    0.59
     />
    0.55
     type
    0.54
    ;
    0.50
     sinon
    0.47
     "@
    0.47
     covariant
    0.47
     tentang
    0.46
    >,
    0.45
     acerca
    0.45
    Act Density 0.002%

    No Known Activations