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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    363
    -0.07
     counts
    -0.07
     Unix
    -0.06
    يم
    -0.06
     سلس
    -0.06
     alike
    -0.06
    Unix
    -0.06
     Allan
    -0.06
    -С
    -0.06
    _bed
    -0.06
    POSITIVE LOGITS
                            
↵
    0.06
     Across
    0.06
    @@
    0.06
    lication
    0.06
    (filePath
    0.06
     municipality
    0.06
    ",&
    0.06
     SST
    0.06
     tension
    0.05
    .docker
    0.05
    Act Density 0.004%

    No Known Activations