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

    Neuronpedia

    INDEX
    Explanations

    Media references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     třídy
    -0.07
    (Window
    -0.07
     Kat
    -0.06
    KD
    -0.06
    _DEFINITION
    -0.06
    Ч
    -0.06
     visions
    -0.06
    Це
    -0.06
     SPE
    -0.06
    Stencil
    -0.06
    POSITIVE LOGITS
    _vert
    0.06
    _PAIR
    0.06
    сий
    0.06
     česk
    0.06
     českých
    0.06
     frau
    0.06
     옆
    0.06
     �
    0.06
     ріш
    0.06
     erupted
    0.06
    Act Density 0.010%

    No Known Activations