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

    Neuronpedia

    INDEX
    Explanations

    bacon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Compar
    1.30
    ok
    1.24
     Cots
    1.24
    ↵
    1.22
     Concerns
    1.21
     Cli
    1.17
     Victims
    1.16
    y
    1.13
     Exhibits
    1.13
     infect
    1.10
    POSITIVE LOGITS
    ف
    1.71
    त
    1.36
    𝓽
    1.33
    $%
    1.31
    ر
    1.29
    ह
    1.28
    মনসিংহ
    1.23
    ี
    1.23
    ิน
    1.21
    1.20
    Act Density 0.002%

    No Known Activations