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

    Neuronpedia

    INDEX
    Explanations

    requests for help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.69
    
    -0.66
     }))
    -0.62
     &___
    -0.62
    taobao
    -0.61
    $}}
    -0.59
    سطس
    -0.58
    Ours
    -0.58
     Help
    -0.57
    protoimpl
    -0.57
    POSITIVE LOGITS
     your
    0.83
    your
    0.57
    ModelAdmin
    0.51
     YOUR
    0.49
     yo
    0.47
    andExpect
    0.46
    riever
    0.46
    YOUR
    0.46
    Биография
    0.44
    RegressionTest
    0.43
    Act Density 0.004%

    No Known Activations