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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or determination based on evidence

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

    making conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.66
    PYX
    -0.65
    expandindo
    -0.65
    )"),
    -0.63
     Normdatei
    -0.62
    }*/
    -0.61
     мәкал
    -0.61
    ])));
    -0.60
    })));
    -0.60
    )]);
    -0.60
    POSITIVE LOGITS
    ActionCreators
    0.45
    AddWithValue
    0.45
     nadzieję
    0.41
     faptul
    0.41
     indicated
    0.35
     יוד
    0.32
     that
    0.32
     know
    0.31
    oneofs
    0.31
    SequentialGroup
    0.31
    Act Density 0.391%

    No Known Activations