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

    Neuronpedia

    INDEX
    Explanations

    business and real-estate

    np_max-act · gemini-2.0-flash

    This neuron primarily responds to occurrences of the word “companies.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HPV
    -0.07
    nj
    -0.06
    eki
    -0.06
     هش
    -0.06
    стра
    -0.06
     billion
    -0.06
     Android
    -0.06
    grim
    -0.06
     tanto
    -0.06
    quoi
    -0.06
    POSITIVE LOGITS
    )(_
    0.07
    )"↵
    0.07
     picked
    0.06
    .transpose
    0.06
    town
    0.06
    !
↵
    0.06
     []↵
    0.06
     incentiv
    0.06
    _compute
    0.06
     neighbours
    0.06
    Act Density 0.044%

    No Known Activations