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

    Neuronpedia

    INDEX
    Explanations

    counting

    np_max-act · gemini-2.0-flash

    conditional statements within code.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the literal question‐label “Q:” that marks the start of a new question.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ANGLES
    -0.07
    蕉
    -0.06
     asla
    -0.06
     плот
    -0.06
     Sid
    -0.06
    uppercase
    -0.06
    ाण
    -0.06
     etmektedir
    -0.06
    ckill
    -0.06
    ogen
    -0.05
    POSITIVE LOGITS
     Threads
    0.07
     Bundy
    0.07
    agement
    0.07
    azon
    0.06
    Management
    0.06
     debuted
    0.06
    [:-
    0.06
    	P
    0.06
    ��
    0.06
    .setting
    0.06
    Act Density 0.007%

    No Known Activations