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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of similarity (e.g. “similarity,” “similar,” “similarities”) in the context of recommendation algorithms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Guantanamo
    -0.07
    	cnt
    -0.06
     lu
    -0.06
     ultrasound
    -0.06
    >
    -0.06
    jte
    -0.06
     Ala
    -0.06
    emo
    -0.06
    .MixedReality
    -0.06
    grown
    -0.06
    POSITIVE LOGITS
    ruh
    0.07
     đẹp
    0.06
    가능
    0.06
    _posts
    0.06
    _define
    0.06
    enger
    0.06
     Gum
    0.06
     �
    0.06
    '),↵
    0.06
     _↵↵
    0.06
    Act Density 0.024%

    No Known Activations