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

    Neuronpedia

    INDEX
    Explanations

    lines of computer code related to parameters and names

    oai_token-act-pair · gemini-2.0-flash

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -2.36
    /*
    -0.65
     the
    -0.62
    __':
    -0.59
    __":
    -0.57
     initComponents
    -0.56
    /**
    -0.56
    The
    -0.56
    '}>
    -0.54
    '
    -0.52
    POSITIVE LOGITS
     Trunks
    0.46
     userModel
    0.46
     numerus
    0.45
     Tent
    0.45
     population
    0.44
    likan
    0.43
    bios
    0.43
    population
    0.42
    !..
    0.42
     Beetle
    0.42
    Act Density 0.172%

    No Known Activations