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

    Neuronpedia

    INDEX
    Explanations

    conditional clauses and logical operators in programming or formal language context

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

    Punctuation, symbols, and code snippets

    np_acts-logits-general · gemini-2.0-flash

    conditional clauses or ellipses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </caption>
    -0.94
    '},
    -0.86
    zzleHttp
    -0.79
     незавершена
    -0.79
    NUMX
    -0.76
    ſelf
    -0.75
    .",
    -0.74
     itſelf
    -0.73
    ſelves
    -0.73
    الدراسه
    -0.73
    POSITIVE LOGITS
    ...
    1.19
    …
    1.14
    ....
    1.05
    ……
    1.03
    ..
    1.01
    .....
    0.98
    ......
    0.96
    :
    0.94
    …..
    0.93
    ….
    0.92
    Act Density 0.368%

    No Known Activations