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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expl
    -0.06
    .Slice
    -0.06
     Lem
    -0.06
    ental
    -0.06
    ToLocal
    -0.06
     Hang
    -0.06
    _Property
    -0.06
     ζω
    -0.06
     peas
    -0.06
    ackson
    -0.06
    POSITIVE LOGITS
     uri
    0.07
     musí
    0.07
    respuesta
    0.07
     jedním
    0.06
     çıktı
    0.06
    (dp
    0.06
    (hwnd
    0.06
     اين
    0.06
     пра
    0.06
    Bl
    0.06
    Act Density 0.017%

    No Known Activations