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

    Neuronpedia

    INDEX
    Explanations

    the word "unique" in code.

    oai_token-act-pair · gemini-2.0-flash

    unique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.68
     arşivlendi
    -0.65
     <<<<<<<<<<<<<<
    -0.53
     BigNumberish
    -0.53
     Quo
    -0.50
    mast
    -0.49
    ScopeManager
    -0.49
     "/")
    -0.49
    νή
    -0.49
    @_
    -0.49
    POSITIVE LOGITS
    HasAnnotation
    0.83
    astify
    0.70
     AssemblyVersion
    0.68
     betweenstory
    0.67
     '\\;'
    0.66
    <bos>
    0.65
    sidemargin
    0.65
    VersionUID
    0.60
    SBATCH
    0.59
    migrationBuilder
    0.59
    Act Density 0.665%

    No Known Activations