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

    Neuronpedia

    INDEX
    Explanations

    Java-related programming structures and constructs

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    closing braces and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.04
    ^(@)
    -0.92
    ſelf
    -0.90
     ་་
    -0.90
    nefs
    -0.89
     ―――――
    -0.89
     photolibrary
    -0.88
    ſelves
    -0.88
     \\
    -0.86
    neſs
    -0.84
    POSITIVE LOGITS
    <eos>
    1.02
    …
    0.78
    ……
    0.77
    ...
    0.76
    }
    0.75
     ...
    0.74
     @
    0.71
    ......
    0.70
     <
    0.70
    </em>
    0.70
    Act Density 0.153%

    No Known Activations