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

    Neuronpedia

    INDEX
    Explanations

    words that are often used when writing scientific papers and research

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.72
    SourceChecksum
    -0.72
    UnusedPrivate
    -0.63
    GOTREF
    -0.57
     Sand
    -0.52
    mybatisplus
    -0.52
    requestCode
    -0.52
    Ос
    -0.51
     án
    -0.50
    WriteTagHelper
    -0.50
    POSITIVE LOGITS
    řízen
    0.57
     steder
    0.57
    nalité
    0.56
     mourut
    0.55
     anledning
    0.54
     orgullo
    0.53
     kvinna
    0.53
     debole
    0.52
    mbor
    0.52
     honte
    0.52
    Act Density 0.795%

    No Known Activations