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

    Neuronpedia

    INDEX
    Explanations

    relatedness

    np_max-act · gemini-2.0-flash

    This neuron activates on the phrase “relevant to,” i.e., it detects occurrences of the term “relevant to.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Thursday
    -0.07
     Cunningham
    -0.07
    userData
    -0.07
     booked
    -0.06
    _old
    -0.06
    Anonymous
    -0.06
    ########################################################
    -0.06
     نسب
    -0.06
    てる
    -0.06
     Churches
    -0.06
    POSITIVE LOGITS
    agini
    0.06
     Red
    0.06
     αγα
    0.06
     rob
    0.06
    bsd
    0.06
     пят
    0.06
    افة
    0.06
     非
    0.06
    -val
    0.06
     suprem
    0.06
    Act Density 0.026%

    No Known Activations