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

    Neuronpedia

    INDEX
    Explanations

    7B models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蓥
    0.47
    बंधनाच्या
    0.42
     Excuse
    0.41
     দীননাথ
    0.40
    nější
    0.39
    ære
    0.39
    ܥ
    0.38
    ině
    0.38
    ėj
    0.37
    കസ
    0.37
    POSITIVE LOGITS
     VN
    0.67
     VC
    0.62
     V
    0.60
     VCS
    0.56
     VH
    0.53
     VF
    0.53
     VD
    0.50
     vn
    0.50
     VV
    0.50
     Vn
    0.48
    Act Density 0.094%

    No Known Activations