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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions, decisions, and states of being

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

    read-modify-write, blink and you miss, kill to eat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.59
    IntoConstraints
    -0.53
    featureID
    -0.51
    sizeCache
    -0.50
    :✨
    -0.50
     surla
    -0.49
    -0.47
     referrerpolicy
    -0.47
    ArrowToggle
    -0.47
     Desc
    -0.47
    POSITIVE LOGITS
    Externé
    0.46
     ocasião
    0.42
     judiciales
    0.41
     pinggang
    0.38
     confiança
    0.36
     raça
    0.36
     trattato
    0.36
    judic
    0.35
     kunci
    0.35
     riuscito
    0.34
    Act Density 0.121%

    No Known Activations