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

    Neuronpedia

    INDEX
    Explanations

    interpersonal connections and shared experiences

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

    phases or stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aronder
    -0.35
    untut
    -0.34
    远
    -0.33
    칭
    -0.32
     thử
    -0.32
     STOCK
    -0.31
    开门
    -0.31
    reib
    -0.31
    配
    -0.30
    ản
    -0.30
    POSITIVE LOGITS
    SequentialGroup
    0.54
     phases
    0.53
    phase
    0.52
    IUrlHelper
    0.52
    StoryboardSegue
    0.51
     चीज़ों
    0.51
    PHASE
    0.50
     fases
    0.50
     oprot
    0.50
    phases
    0.50
    Act Density 0.096%

    No Known Activations