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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /A
    -0.07
    dain
    -0.07
    式会社
    -0.07
     first
    -0.06
    3
    -0.06
    first
    -0.06
     vo
    -0.06
    รวจ
    -0.06
    entreprise
    -0.06
     APS
    -0.06
    POSITIVE LOGITS
    ouston
    0.07
    파일
    0.07
    .Tensor
    0.06
    395
    0.06
    -lines
    0.06
     getSession
    0.06
     UClass
    0.06
     рамках
    0.06
    Latin
    0.06
     своїх
    0.06
    Act Density 0.103%

    No Known Activations