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

    Neuronpedia

    INDEX
    Explanations

    start () function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    th
    0.60
    us
    0.48
    the
    0.47
    ah
    0.45
    и
    0.43
    ли
    0.42
    </td>
    0.42
    5
    0.42
     The
    0.42
    x
    0.42
    POSITIVE LOGITS
     histórias
    0.45
     realises
    0.43
     biopsies
    0.42
     apopt
    0.42
     piercings
    0.41
     dicas
    0.41
    kład
    0.41
     ouverte
    0.41
     bilg
    0.40
     entrevistas
    0.40
    Act Density 0.002%

    No Known Activations