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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    语言
    -0.07
     storage
    -0.07
     adher
    -0.07
     STREET
    -0.06
     checkout
    -0.06
    -blocking
    -0.06
     assembled
    -0.06
    aks
    -0.06
     Ваш
    -0.06
     kappa
    -0.06
    POSITIVE LOGITS
    lesc
    0.07
    minster
    0.06
     penny
    0.05
    .ReadToEnd
    0.05
    noc
    0.05
     (?)
    0.05
     bì
    0.05
     Fors
    0.05
    mesini
    0.05
     Clover
    0.05
    Act Density 0.066%

    No Known Activations