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

    Neuronpedia

    INDEX
    Explanations

    debugging statements and logging information within code snippets

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

    Code and programming-related text

    np_acts-logits-general · gemini-2.0-flash

    programming method calls and returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.06
    .";
    -0.87
    Portail
    -0.86
    ."</
    -0.85
    ".
    -0.84
    .",
    -0.83
    )':
    -0.82
     />';
    -0.82
    '],
    -0.81
    httphttps
    -0.81
    POSITIVE LOGITS
     got
    0.69
     inside
    0.67
    ==
    0.67
    ----
    0.65
    ====
    0.65
     ==
    0.65
     ---
    0.64
     size
    0.62
    inside
    0.61
     --
    0.61
    Act Density 0.146%

    No Known Activations