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

    Neuronpedia

    INDEX
    Explanations

    terms associated with significant or innovative developments

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

    new and important advancements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoField
    -0.45
    bootstrapcdn
    -0.42
     sembl
    -0.40
     Wishing
    -0.40
     pomme
    -0.39
    mtrl
    -0.39
    \{\\
    -0.39
    onymie
    -0.38
     procra
    -0.38
     stamps
    -0.37
    POSITIVE LOGITS
     groundbreaking
    1.42
     pioneering
    1.00
     revolutionary
    0.87
     innovative
    0.84
     breakthrough
    0.79
    innovative
    0.78
     landmark
    0.78
    revolutionary
    0.75
     pione
    0.73
     breakthroughs
    0.73
    Act Density 0.004%

    No Known Activations