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

    Neuronpedia

    INDEX
    Explanations

    comparative language indicating an increase or enhancement

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

    following "more" indicating comparison

    np_acts-logits-general · gemini-2.0-flash

    more X than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.82
     réfugi
    -0.70
     blessés
    -0.64
     supplémentaire
    -0.64
     engraçadas
    -0.63
     gyhoeddwyd
    -0.63
    ️
    -0.62
     pequenas
    -0.61
     moindre
    -0.61
     CascadeType
    -0.60
    POSITIVE LOGITS
     than
    0.89
     frequent
    0.80
     efficient
    0.80
     likely
    0.77
     pronounced
    0.74
     often
    0.71
     complicated
    0.70
     elaborate
    0.70
     easily
    0.69
     importantly
    0.68
    Act Density 0.168%

    No Known Activations