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

    Neuronpedia

    INDEX
    Explanations

    code, either mathematical or in a programming language, involving variables i, j, x, and y

    oai_token-act-pair · gemini-2.0-flash

    code variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.57
    ьаж
    -0.54
     незавершена
    -0.49
    phonie
    -0.44
     Sénat
    -0.43
    oporosis
    -0.42
    ंदीखरीदारी
    -0.42
    ️
    -0.41
    utilisons
    -0.41
     الدولى
    -0.41
    POSITIVE LOGITS
    ParallelGroup
    0.67
    LookAnd
    0.62
    Browsable
    0.59
     Signalez
    0.57
    ExecuteReader
    0.57
    npmjs
    0.55
    copa
    0.54
    RTCK
    0.54
    complexContent
    0.53
    EndInit
    0.53
    Act Density 0.570%

    No Known Activations