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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and syntax.

    oai_token-act-pair · gemini-2.0-flash

    Code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inconsistency
    -0.56
     interchangeably
    -0.54
     carelessness
    -0.53
     contradictory
    -0.52
    considering
    -0.51
     indifference
    -0.50
     mobilisation
    -0.50
     valmis
    -0.50
     meille
    -0.49
     reviving
    -0.49
    POSITIVE LOGITS
    logrus
    0.56
    bukkit
    0.54
    gms
    0.54
    BASEPATH
    0.53
    rdd
    0.52
    ukone
    0.52
    gpl
    0.52
    stdc
    0.52
    bsd
    0.52
    gh
    0.51
    Act Density 26.946%

    No Known Activations