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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to planning and management processes

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

    ending in "-ing" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    actions and their contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.63
    ContextHolder
    -0.63
     ModelExpression
    -0.63
     AssemblyProduct
    -0.60
    InstanceState
    -0.60
    GEBURTS
    -0.60
    存于互联网档案馆
    -0.59
    ftagPool
    -0.58
     thence
    -0.55
     jadx
    -0.54
    POSITIVE LOGITS
     the
    1.10
     your
    1.07
     their
    0.84
     a
    0.84
     an
    0.79
     our
    0.77
     purposes
    0.75
     techniques
    0.74
     of
    0.71
     his
    0.70
    Act Density 0.425%

    No Known Activations