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

    Neuronpedia

    INDEX
    Explanations

    references to specific studies or evaluations in scientific literature

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

    preceding conjunctions "and" or "nor"

    np_acts-logits-general · gemini-2.0-flash

    and, nor, connecting clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.52
    levance
    -0.51
     validity
    -0.47
    onade
    -0.46
    obox
    -0.46
     Continuity
    -0.46
    sibilità
    -0.45
    先后
    -0.45
     prolongation
    -0.45
     invalidate
    -0.45
    POSITIVE LOGITS
     extremely
    1.03
     very
    0.98
     highly
    0.95
     able
    0.94
     capable
    0.89
    extremely
    0.88
     lacking
    0.86
    Искәрмәләр
    0.83
     VERY
    0.82
     ready
    0.82
    Act Density 0.586%

    No Known Activations