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

    Neuronpedia

    INDEX
    Explanations

    professional roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tuple
    0.56
    utas
    0.56
    help
    0.53
    args
    0.51
    section
    0.51
    format
    0.50
     tuple
    0.50
    opcode
    0.50
    access
    0.49
    answers
    0.49
    POSITIVE LOGITS
     Analyst
    0.69
     אני
    0.63
     Photographer
    0.63
     Profesor
    0.61
     ми
    0.58
     senador
    0.58
     journaliste
    0.58
     peintre
    0.58
     actriz
    0.57
     Schriftsteller
    0.57
    Act Density 0.023%

    No Known Activations