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

    Neuronpedia

    INDEX
    Explanations

    solving

    np_max-act · gemini-2.0-flash

    phrases related to scientific qualifications and credentials.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	ASSERT
    -0.07
    _topology
    -0.07
     definition
    -0.07
    (bl
    -0.06
     qed
    -0.06
    ckt
    -0.06
    *(
    -0.06
    _vector
    -0.06
    ุง
    -0.06
    -offset
    -0.06
    POSITIVE LOGITS
    _OBJ
    0.07
     proficient
    0.07
    正确
    0.06
     hurt
    0.06
     Resolve
    0.06
     miles
    0.06
    liked
    0.06
    iating
    0.06
     Longitude
    0.06
    avoid
    0.06
    Act Density 0.010%

    No Known Activations