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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хоча
    -0.07
     द
    -0.07
    _learning
    -0.06
     Quest
    -0.06
     MEMORY
    -0.06
    (ptr
    -0.06
     induces
    -0.06
     المح
    -0.06
     overloaded
    -0.06
    square
    -0.06
    POSITIVE LOGITS
     why
    0.07
     ','
    0.07
    binations
    0.06
    btc
    0.06
    せて
    0.06
     держав
    0.06
    (Web
    0.06
    ibly
    0.06
    _jButton
    0.06
    chars
    0.06
    Act Density 0.004%

    No Known Activations