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

    Neuronpedia

    INDEX
    Explanations

    package prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    comodule
    0.36
    castellan
    0.35
    𒁀
    0.35
    𒈠
    0.34
    唥
    0.33
    咊
    0.32
    LOTRE
    0.32
    براير
    0.32
     მიმო
    0.32
     lymphatiques
    0.31
    POSITIVE LOGITS
     "
    0.39
     T
    0.39
     Soft
    0.39
     the
    0.38
    0.38
     L
    0.37
     Software
    0.36
     Z
    0.36
     a
    0.36
     B
    0.36
    Act Density 0.000%

    No Known Activations