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

    Neuronpedia

    INDEX
    Explanations

    company

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TT
    -0.06
     Fiscal
    -0.06
     sunt
    -0.06
    TT
    -0.06
    ируется
    -0.06
    Poll
    -0.06
     riff
    -0.06
    𝒗
    -0.06
    forest
    -0.06
     설정
    -0.06
    POSITIVE LOGITS
     dreaming
    0.07
    successful
    0.07
     ödeme
    0.07
     PLA
    0.07
     WPARAM
    0.07
    熬夜
    0.07
    裈
    0.06
     success
    0.06
    缎
    0.06
     forging
    0.06
    Act Density 0.019%

    No Known Activations