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

    Neuronpedia

    INDEX
    Explanations

    Swirl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stap
    -0.07
     Lent
    -0.07
     опред
    -0.06
     adapt
    -0.06
    ugador
    -0.06
     isim
    -0.06
    dere
    -0.06
     lect
    -0.06
    =_('
    -0.06
    /name
    -0.06
    POSITIVE LOGITS
     swirling
    0.15
     swirl
    0.12
     whirl
    0.09
     vortex
    0.08
    WC
    0.08
     جلس
    0.07
    �
    0.07
     zm
    0.07
     carries
    0.07
     gl
    0.07
    Act Density 0.004%

    No Known Activations