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

    Neuronpedia

    INDEX
    Explanations

    different forms of comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code comments or headers

    np_acts-logits-general · gemini-2.0-flash

    cannot make any guesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.80
    rrggbb
    -0.72
     الرياضيه
    -0.60
     GenerationType
    -0.60
    ManyToMany
    -0.59
    AndEndTag
    -0.56
    qJ
    -0.53
    āng
    -0.52
    alipay
    -0.52
    ofas
    -0.52
    POSITIVE LOGITS
    ****************
    1.43
    *******
    0.82
    ********
    0.78
    **************
    0.76
    ***************
    0.76
    ******/
    0.75
    *****
    0.75
    ******
    0.75
    ****
    0.73
    ************
    0.72
    Act Density 0.106%

    No Known Activations