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

    Neuronpedia

    INDEX
    Explanations

    commas and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $m
    -0.07
    environments
    -0.07
    827
    -0.06
    .getAs
    -0.06
    CAS
    -0.06
    -plugins
    -0.06
     학교
    -0.06
    keiten
    -0.06
    907
    -0.06
    584
    -0.06
    POSITIVE LOGITS
     preceded
    0.07
     FIR
    0.06
    .badlogic
    0.06
    انی
    0.06
     rip
    0.06
     suited
    0.06
    (index
    0.06
     finds
    0.06
     repent
    0.06
     marshal
    0.06
    Act Density 0.027%

    No Known Activations