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

    Neuronpedia

    INDEX
    Explanations

    objective-c code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সম্পদ
    0.42
     द्रव्य
    0.40
    ادار
    0.39
     Luisa
    0.39
     barons
    0.38
     Sita
    0.37
     Jésus
    0.37
     viendo
    0.37
    ﭜ
    0.37
    lomer
    0.36
    POSITIVE LOGITS
    @
    0.69
     static
    0.59
    static
    0.57
     @
    0.56
     imported
    0.50
    ...@
    0.50
    @{
    0.46
    \@
    0.46
    @",
    0.42
    =@
    0.42
    Act Density 0.001%

    No Known Activations