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

    Neuronpedia

    INDEX
    Explanations

    com.example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    phalodes
    0.48
    necks
    0.47
     vésicules
    0.47
    ünk
    0.46
    মের
    0.46
    ètes
    0.45
     komponent
    0.45
    ெற்ற
    0.45
     mécanismes
    0.44
    pyrimidine
    0.43
    POSITIVE LOGITS
     q
    0.43
    此
    0.43
     приносит
    0.41
     Second
    0.40
    ↵
    0.40
     आठ
    0.40
     World
    0.39
    Upload
    0.39
    Supply
    0.39
    做
    0.39
    Act Density 0.000%

    No Known Activations