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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to cleanliness and regulations

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

    negation or contrast

    np_acts-logits-general · gemini-2.0-flash

    and or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.66
     betweenstory
    -0.64
    })));
    -0.60
     favourably
    -0.59
    ThroughAttribute
    -0.57
    homonymie
    -0.56
     @}
    -0.56
    ₁)
    -0.56
    曖昧さ回避
    -0.55
     favorably
    -0.55
    POSITIVE LOGITS
     non
    0.67
    そうで
    0.64
     not
    0.57
     CURIAM
    0.57
    SequentialGroup
    0.55
     sebaliknya
    0.51
     Not
    0.50
     NOT
    0.50
     Non
    0.49
    достатки
    0.48
    Act Density 0.376%

    No Known Activations