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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    np_max-act · gemini-2.0-flash

    This neuron activates on proper names or name-like tokens (i.e. personal or character names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     primes
    -0.06
     Titan
    -0.06
    olves
    -0.06
    练
    -0.06
    險
    -0.06
    mail
    -0.06
    ベ
    -0.06
     nelle
    -0.06
    _teams
    -0.06
    instruction
    -0.06
    POSITIVE LOGITS
     jj
    0.08
    rtle
    0.07
     Katrina
    0.07
     нен
    0.07
     Комп
    0.07
    =this
    0.06
    =\""
    0.06
    //"
    0.06
     vůbec
    0.06
    ुकस
    0.06
    Act Density 0.143%

    No Known Activations