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

    Neuronpedia

    INDEX
    Explanations

    analogies and comparisons

    np_max-act · gemini-2.0-flash

    This neuron activates specifically on the words “lasagna” and “helicopter.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     який
    -0.07
    _single
    -0.07
     tons
    -0.06
     healed
    -0.06
    ріб
    -0.06
     уклад
    -0.06
     negligence
    -0.06
     Budd
    -0.06
     basal
    -0.06
    Children
    -0.06
    POSITIVE LOGITS
    :".$
    0.07
    تور
    0.07
    ONENT
    0.06
     Appears
    0.06
     Pic
    0.06
    坦
    0.06
    ぎ
    0.06
    jn
    0.06
    PE
    0.06
    KS
    0.06
    Act Density 0.062%

    No Known Activations