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

    Neuronpedia

    INDEX
    Explanations

    direct + following word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Director
    0.61
     Director
    0.61
     DIRECTOR
    0.57
     director
    0.56
     directeur
    0.52
     directors
    0.50
     директора
    0.50
     директор
    0.50
    Directory
    0.48
     Directeur
    0.48
    POSITIVE LOGITS
    orship
    0.77
    ives
    0.74
    ivity
    0.69
     confrontation
    0.67
    ively
    0.64
     confrontations
    0.57
     proportionally
    0.56
    iveness
    0.55
    ivities
    0.54
     proportionality
    0.53
    Act Density 0.054%

    No Known Activations