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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the presence of the choice label “C.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    phrases related to interpersonal relationships and social behaviors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	values
    -0.07
    ndef
    -0.06
    .street
    -0.06
     partic
    -0.06
    valid
    -0.06
    ..'
    -0.06
     survives
    -0.06
     struct
    -0.06
    524
    -0.06
    productos
    -0.06
    POSITIVE LOGITS
    擦
    0.07
    羊
    0.06
     Cunningham
    0.06
     categorical
    0.06
     Xuân
    0.06
     basket
    0.06
     проблемы
    0.06
     світ
    0.06
     інт
    0.06
     Sox
    0.06
    Act Density 0.001%

    No Known Activations