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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASK
    -0.07
    Conditional
    -0.06
     immutable
    -0.06
     einfach
    -0.06
    Adam
    -0.06
    Foo
    -0.06
     dormant
    -0.06
     parçası
    -0.06
     productive
    -0.06
    ücken
    -0.06
    POSITIVE LOGITS
     Chest
    0.07
     autorelease
    0.06
    �
    0.06
     distress
    0.06
    $xml
    0.06
     leisure
    0.06
     Career
    0.06
     A
    0.06
    A
    0.06
    Recognizer
    0.06
    Act Density 0.003%

    No Known Activations