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

    Neuronpedia

    INDEX
    Explanations

    game theory, sharing, benefits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amplifier
    -0.07
     Sales
    -0.07
    Knowing
    -0.07
    ienes
    -0.06
    nist
    -0.06
     Once
    -0.06
    coat
    -0.06
    .／
    -0.06
    CSR
    -0.06
     SCALE
    -0.06
    POSITIVE LOGITS
     Pemb
    0.07
     AssemblyProduct
    0.06
     graphite
    0.06
    (search
    0.06
    ومات
    0.06
     관
    0.06
    lut
    0.06
    Mt
    0.06
    ्य
    0.06
     Merkez
    0.06
    Act Density 0.002%

    No Known Activations