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

    Neuronpedia

    INDEX
    Explanations

    three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NBA
    -0.08
    ocalyptic
    -0.07
    319
    -0.07
     diffs
    -0.07
     ViewChild
    -0.07
     servlet
    -0.07
    oretical
    -0.07
     HttpURLConnection
    -0.07
     ú
    -0.06
    ladığı
    -0.06
    POSITIVE LOGITS
     tailor
    0.07
    MASK
    0.07
    (Operation
    0.06
     directly
    0.06
    gate
    0.06
    habit
    0.06
    .ret
    0.06
     soon
    0.06
    .and
    0.06
    UD
    0.06
    Act Density 0.008%

    No Known Activations