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

    Neuronpedia

    INDEX
    Explanations

    words and phrases with unusual or fantastical elements

    oai_token-act-pair · gemini-2.0-flash

    pasta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WIG
    -0.51
    principalColumn
    -0.50
    ))]
    -0.49
     发表于
    -0.47
    ])]
    -0.44
     reman
    -0.44
     مرئيه
    -0.44
    élien
    -0.43
    acté
    -0.43
    atzung
    -0.43
    POSITIVE LOGITS
    writeField
    0.65
    BufferException
    0.65
     AssemblyVersion
    0.60
     tombé
    0.54
     Hoffnung
    0.53
    SequentialGroup
    0.53
    WaitGroup
    0.52
     innamor
    0.52
     russes
    0.52
     niyang
    0.50
    Act Density 1.772%

    No Known Activations