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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash

    positive affirmations related to supportive behaviors in relationships.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    azine
    -0.08
     rice
    -0.07
     Brushes
    -0.07
    파트
    -0.06
     relation
    -0.06
    plt
    -0.06
    -groups
    -0.06
    "]],↵
    -0.06
     forces
    -0.06
    perience
    -0.06
    POSITIVE LOGITS
    /Y
    0.06
    ラック
    0.06
    _TMP
    0.06
    ратно
    0.06
     HE
    0.06
    	ad
    0.06
     ،
    0.06
     čtvrt
    0.06
    Inlining
    0.06
     QB
    0.06
    Act Density 0.002%

    No Known Activations