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

    Neuronpedia

    INDEX
    Explanations

    branded products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     言っ
    0.43
    页面存档备份
    0.34
    कल्चर
    0.34
    टीशन
    0.33
    甠
    0.32
    न्हें
    0.31
    agamanam
    0.31
    眹
    0.31
    跇
    0.31
     सश
    0.30
    POSITIVE LOGITS
    0.48
    ®
    0.42
    3
    0.41
    5
    0.41
    6
    0.40
     F
    0.39
    1
    0.39
    4
    0.38
     V
    0.38
     latest
    0.38
    Act Density 0.138%

    No Known Activations