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

    Neuronpedia

    INDEX
    Explanations

    discrepancies or issues in the context of various topics, often highlighting comparisons and evaluations

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

    Punctuation followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    punctuation and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.82
    ImageContext
    -0.78
    astify
    -0.76
     "")
    -0.75
     }}"></
    -0.73
     @"";
    -0.72
    ]+=
    -0.70
    ")==
    -0.69
    "");
    -0.68
     ویکی‌پدی
    -0.67
    POSITIVE LOGITS
     my
    1.43
     mine
    1.25
    my
    1.17
     I
    1.08
     comigo
    0.97
     minha
    0.96
    私は
    0.96
     meiner
    0.95
     моего
    0.95
     мой
    0.91
    Act Density 0.355%

    No Known Activations