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

    Neuronpedia

    INDEX
    Explanations

    number or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     material
    0.43
    稱
    0.41
     resource
    0.41
    tym
    0.39
     area
    0.38
    ene
    0.38
    urada
    0.38
     design
    0.38
    че
    0.38
     water
    0.37
    POSITIVE LOGITS
     Mikel
    0.47
     effectuées
    0.47
    𒋢
    0.47
     compiles
    0.45
    க்கிர
    0.44
     fonbet
    0.44
    LayoutInflater
    0.43
     někol
    0.43
     PROCED
    0.42
    흰
    0.42
    Act Density 0.000%

    No Known Activations