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

    Neuronpedia

    INDEX
    Explanations

    words related to procedures and methodology ("technique")

    oai_token-act-pair · gemini-2.0-flash

    technique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    a
    -0.84
    S
    -0.82
    <bos>
    -0.79
    os
    -0.75
    o
    -0.75
    R
    -0.75
    ly
    -0.73
    ness
    -0.73
    A
    -0.72
    Y
    -0.71
    POSITIVE LOGITS
    etheless
    0.99
    onucleotide
    0.93
    EDEFAULT
    0.88
    orrho
    0.85
    richlet
    0.84
    ourite
    0.84
    ymce
    0.83
    neighbour
    0.83
     AssemblyCulture
    0.81
    ORIAL
    0.80
    Act Density 4.224%

    No Known Activations