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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming syntax, possibly including exception handling, conditional statements, and file input/output.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.90
    ↵
    -0.50
    hu
    -0.46
     tuần
    -0.45
    нибудь
    -0.44
    yo
    -0.43
    ect
    -0.42
    mann
    -0.41
    rist
    -0.41
    zu
    -0.40
    POSITIVE LOGITS
     Efq
    0.81
     InputDecoration
    0.62
    Читати
    0.62
     Monfieur
    0.57
     Theſe
    0.56
     becauſe
    0.55
    MemoryWarning
    0.54
     ftate
    0.54
     fhew
    0.53
     avoient
    0.51
    Act Density 0.136%

    No Known Activations