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

    Neuronpedia

    INDEX
    Explanations

    speculative biology and influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.63
    in
    0.62
    en
    0.61
    can
    0.61
    ut
    0.59
    add
    0.58
    A
    0.58
    one
    0.58
    il
    0.57
    top
    0.56
    POSITIVE LOGITS
     paralysie
    0.61
     voisines
    0.55
     employability
    0.54
    یسر
    0.54
     embarazo
    0.54
     melhorar
    0.52
    وترات
    0.52
     pattes
    0.51
    ---’
    0.50
     marihuana
    0.50
    Act Density 0.001%

    No Known Activations