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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _documento
    -0.07
     hotel
    -0.07
     automobile
    -0.07
     mice
    -0.07
     whats
    -0.06
     Sort
    -0.06
     fashion
    -0.06
     disponibles
    -0.06
     amassed
    -0.06
     nord
    -0.06
    POSITIVE LOGITS
     Katy
    0.07
    fib
    0.07
    userManager
    0.06
    .HashMap
    0.06
     Concat
    0.06
    ouncy
    0.06
    _LSB
    0.06
     designers
    0.06
    ENOMEM
    0.06
    kat
    0.06
    Act Density 0.021%

    No Known Activations