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

    Neuronpedia

    INDEX
    Explanations

    doctorates and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    髀
    0.42
    嚶
    0.40
    firefox
    0.39
     trajet
    0.39
    corto
    0.39
    authored
    0.39
    aceted
    0.38
    始める
    0.38
    attaque
    0.38
     anisot
    0.38
    POSITIVE LOGITS
     titles
    0.82
    titles
    0.71
     title
    0.69
     Titles
    0.65
     Esq
    0.65
     MBA
    0.64
     tytu
    0.62
     títulos
    0.61
    Titles
    0.60
     PhD
    0.59
    Act Density 0.013%

    No Known Activations