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

    Neuronpedia

    INDEX
    Explanations

    languages, including Chinese, Thai, Korean, Spanish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    1.19
     the
    1.16
    1.03
      
    1.01
     not
    0.96
     and
    0.93
     in
    0.93
     this
    0.93
    -
    0.92
     (
    0.92
    POSITIVE LOGITS
    Otros
    1.16
    goài
    1.11
    arrerol
    1.11
    Empleado
    1.10
    esorios
    1.09
    extrémité
    1.09
    ayvachi
    1.09
    Liên
    1.07
    <unused40>
    1.06
    Usuario
    1.06
    Act Density 0.052%

    No Known Activations