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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with "only"

    oai_token-act-pair · gemini-2.0-flash

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.71
    SBATCH
    -0.71
    StoryboardSegue
    -0.70
     Monfieur
    -0.69
     itſelf
    -0.69
     myſelf
    -0.69
     raiſ
    -0.69
    stdc
    -0.69
     bocca
    -0.68
     juſt
    -0.68
    POSITIVE LOGITS
    XmlAccessType
    0.68
    SerializedSize
    0.49
    φι
    0.47
    ตร
    0.47
    MathML
    0.47
     ses
    0.46
     EXIST
    0.46
     pé
    0.45
     debug
    0.45
     respe
    0.45
    Act Density 0.108%

    No Known Activations