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

    Neuronpedia

    INDEX
    Explanations

    Morris

    np_max-act · gemini-2.0-flash

    The neuron detects the proper-name token sequence corresponding to "Morris" (i.e., the Mor+ris name tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     onboard
    -0.07
    vasion
    -0.07
    eceğini
    -0.07
     бух
    -0.06
    Под
    -0.06
     inhibition
    -0.06
    .png
    -0.06
    ielding
    -0.06
    援
    -0.06
     seizing
    -0.06
    POSITIVE LOGITS
     Morris
    0.15
     Mor
    0.12
    Mor
    0.11
     Harris
    0.10
     mor
    0.10
     Ellis
    0.09
     Warren
    0.08
     Dor
    0.08
    oris
    0.08
    is
    0.08
    Act Density 0.019%

    No Known Activations