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

    Neuronpedia

    INDEX
    Explanations

    legal documents/redaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рупп
    -0.06
    位于
    -0.06
    ataset
    -0.06
    Decimal
    -0.06
    Twig
    -0.06
    (',
    -0.06
     Evidence
    -0.06
    igen
    -0.06
    (product
    -0.06
    When
    -0.06
    POSITIVE LOGITS
     전세가
    0.06
     �
    0.06
     Angie
    0.06
     goof
    0.06
     реє
    0.06
     subpoena
    0.06
    ."[
    0.06
     tritur
    0.06
     Hussein
    0.06
     analsex
    0.06
    Act Density 0.007%

    No Known Activations