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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    езда
    -0.07
     sausage
    -0.07
    olu
    -0.07
     dlou
    -0.06
    ITIVE
    -0.06
     fre
    -0.06
     PO
    -0.06
    ari
    -0.06
     BEGIN
    -0.06
    ció
    -0.06
    POSITIVE LOGITS
    жа
    0.06
    ение
    0.06
     AudioManager
    0.06
    (&$
    0.06
    ху
    0.06
     />↵
    0.06
    .USER
    0.06
    َق
    0.06
    َم
    0.06
    Asset
    0.06
    Act Density 0.008%

    No Known Activations