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

    Neuronpedia

    INDEX
    Explanations

    IE

    np_max-act · gemini-2.0-flash

    conversations related to purchasing and product recommendations.

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

    This neuron detects the speaker‐turn labels “Interviewer” and “Interviewee” (specifically the “er” and “ee” endings in those labels).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ख
    -0.06
    Middleware
    -0.06
    .WinControls
    -0.06
     �
    -0.06
    ieten
    -0.05
     vyvol
    -0.05
    izmet
    -0.05
     nonce
    -0.05
     Protective
    -0.05
    .getEnd
    -0.05
    POSITIVE LOGITS
    .NaN
    0.06
    186
    0.06
    icken
    0.06
    vant
    0.06
    تغ
    0.06
    _AD
    0.06
    nat
    0.06
    atura
    0.06
     İt
    0.06
    ='/
    0.06
    Act Density 0.029%

    No Known Activations