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

    Neuronpedia

    INDEX
    Explanations

    references to formal structures and mathematical propositions

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

    Theorems, propositions, or assumptions

    np_acts-logits-general · gemini-2.0-flash

    mathematical theorems propositions lemmas assumptions corollaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.53
    ]=="
    -0.52
    \"></
    -0.51
     );
    -0.48
    
    -0.48
     }}>
    -0.47
    Greater
    -0.47
    "):
    -0.47
     mustn
    -0.46
    idd
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.70
    astify
    0.63
     Let
    0.62
    पया
    0.59
     nawr
    0.59
    Hauptartikel
    0.58
     Пусть
    0.57
     Chwiliwch
    0.55
    ConstraintMaker
    0.55
     getItemId
    0.55
    Act Density 0.375%

    No Known Activations