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

    Neuronpedia

    INDEX
    Explanations

    Diverse text sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.87
    GEBURTSDATUM
    -0.79
     autorytatywna
    -0.73
    kháu
    -0.72
    ///</
    -0.71
     feroit
    -0.70
     disambiguazione
    -0.70
     pouvoit
    -0.70
    ArrowToggle
    -0.69
    afficheront
    -0.69
    POSITIVE LOGITS
     great
    0.67
     the
    0.63
     greatest
    0.54
     highest
    0.51
     largest
    0.51
     other
    0.50
     a
    0.50
    ca
    0.50
     smallest
    0.48
     ma
    0.47
    Act Density 0.000%

    No Known Activations