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

    Neuronpedia

    INDEX
    Explanations

    words related to choosing or selecting a particular item from a list

    oai_token-act-pair · gemini-2.0-flash

    selection from a group

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fusca
    -0.70
    IntoConstraints
    -0.69
    ilya
    -0.62
     متحده
    -0.60
     ujednoznacz
    -0.60
     numberOfRows
    -0.57
     versa
    -0.57
    inander
    -0.56
    ddots
    -0.55
    collation
    -0.55
    POSITIVE LOGITS
     those
    0.72
    Those
    0.65
    those
    0.63
    那些
    0.61
     Those
    0.60
     aquellos
    0.60
    RegistryLite
    0.59
     aqueles
    0.58
    queles
    0.48
     THOSE
    0.48
    Act Density 5.629%

    No Known Activations