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

    Neuronpedia

    INDEX
    Explanations

    sorting lists and arrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inos
    0.44
     modello
    0.44
     pranzo
    0.43
     giornal
    0.42
     jardín
    0.42
     welder
    0.42
    我不
    0.42
     prendere
    0.42
     giorno
    0.41
     inizia
    0.41
    POSITIVE LOGITS
    내
    0.47
    ह
    0.46
    shape
    0.45
    Exec
    0.45
     victor
    0.45
    香
    0.44
    ---
    0.44
     घ
    0.44
    ज
    0.43
    TEXT
    0.43
    Act Density 0.038%

    No Known Activations