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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ManyToOne
    -0.07
     player
    -0.07
     Zheng
    -0.07
     pathlib
    -0.06
     голов
    -0.06
     venir
    -0.06
    інки
    -0.06
     terr
    -0.06
    -minded
    -0.06
     Muslims
    -0.06
    POSITIVE LOGITS
     أق
    0.07
    atisfied
    0.07
     training
    0.07
     neon
    0.06
    تش
    0.06
    indy
    0.06
    [:,
    0.06
    τικ
    0.06
    _ad
    0.06
    rina
    0.06
    Act Density 0.005%

    No Known Activations