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

    Neuronpedia

    INDEX
    Explanations

    code snippets, particularly variable assignments and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    special characters or unique formatting elements

    np_token-act-pair-logits · gpt-4o-mini

    Code-related tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    9
    -0.52
     nine
    -0.50
     front
    -0.49
    teins
    -0.48
    щиков
    -0.47
    ふり
    -0.47
    falen
    -0.46
     nueve
    -0.45
     Oh
    -0.45
    essions
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.86
     '\\;'
    0.85
     يتيمه
    0.84
    ########.
    0.81
    tvguidetime
    0.79
    stdc
    0.78
     חיצוניים
    0.74
    SequentialGroup
    0.73
    DockStyle
    0.72
     GenerationType
    0.71
    Act Density 1.244%

    No Known Activations