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
    زا
    -0.07
    fet
    -0.07
    的手
    -0.06
    -room
    -0.06
     đây
    -0.06
    girls
    -0.06
    шир
    -0.06
     excel
    -0.06
    suite
    -0.06
    aura
    -0.06
    POSITIVE LOGITS
    ДА
    0.06
    κης
    0.06
    .SUCCESS
    0.06
     filing
    0.06
     solidity
    0.06
    (receiver
    0.06
     Oasis
    0.05
     Wanted
    0.05
     LPC
    0.05
    AKE
    0.05
    Act Density 0.010%

    No Known Activations