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

    Neuronpedia

    INDEX
    Explanations

    tx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    邪
    -0.07
    全部
    -0.07
    енным
    -0.06
     rew
    -0.06
     Layout
    -0.06
    Customers
    -0.06
     chose
    -0.06
     intellig
    -0.06
    Me
    -0.06
     Ras
    -0.06
    POSITIVE LOGITS
    aceous
    0.07
    serialization
    0.06
     monthly
    0.06
     ylabel
    0.06
    OPS
    0.06
    umar
    0.06
    isper
    0.06
    анны
    0.06
    šky
    0.06
    ίναι
    0.06
    Act Density 0.000%

    No Known Activations