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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vitamins
    -0.08
     pil
    -0.08
     mostrar
    -0.08
     mostr
    -0.07
     surcharge
    -0.07
     viz
    -0.07
    zí
    -0.07
     sort
    -0.07
     krij
    -0.07
     bring
    -0.07
    POSITIVE LOGITS
    manifest
    0.11
    uses
    0.11
     manifestations
    0.10
     Согласно
    0.10
     manifested
    0.10
     manifestation
    0.09
    application
    0.09
     manifests
    0.09
    queries
    0.09
    _manifest
    0.09
    Act Density 0.001%

    No Known Activations