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

    Neuronpedia

    INDEX
    Explanations

    calculus and order by clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.72
    TI
    0.69
    L
    0.62
     provide
    0.60
    ，
    0.59
    PerformLayout
    0.59
    ier
    0.59
    P
    0.58
    us
    0.58
     Br
    0.57
    POSITIVE LOGITS
    in
    0.80
     ausencia
    0.78
    ین
    0.78
     palavras
    0.78
     individuo
    0.77
     inverno
    0.77
     esistono
    0.76
    ното
    0.76
    یف
    0.75
    менти
    0.75
    Act Density 0.003%

    No Known Activations