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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of fundraising or charitable giving (e.g. “raised,” “funds,” “money for”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ाण
    -0.06
    вет
    -0.06
     rupt
    -0.06
    дав
    -0.06
     bandwidth
    -0.06
     Mini
    -0.06
    ，而
    -0.06
     filmmakers
    -0.06
     مخ
    -0.06
     stabil
    -0.06
    POSITIVE LOGITS
     genesis
    0.06
    798
    0.06
     GRA
    0.06
    овой
    0.06
     intern
    0.06
    Positions
    0.06
    insula
    0.06
     locksmith
    0.06
    747
    0.06
    gart
    0.06
    Act Density 0.016%

    No Known Activations