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

    Neuronpedia

    INDEX
    Explanations

    Code/Configuration snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     więcej
    -0.07
     größ
    -0.06
    全面
    -0.06
    ência
    -0.06
    awy
    -0.06
     purch
    -0.06
     LatLng
    -0.06
    itable
    -0.06
    nih
    -0.06
    antics
    -0.06
    POSITIVE LOGITS
    514
    0.07
    ackets
    0.07
     karış
    0.06
    His
    0.06
     signed
    0.06
                                    
    0.06
     tents
    0.06
     linker
    0.06
    Narrated
    0.06
     offer
    0.06
    Act Density 0.052%

    No Known Activations