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

    Neuronpedia

    INDEX
    Explanations

    Niagara Falls

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the proper name “Niagara Falls.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    leaders
    -0.07
     July
    -0.07
     CC
    -0.06
     Time
    -0.06
    .cz
    -0.06
     TIME
    -0.06
    基于
    -0.06
     Jose
    -0.06
     Qing
    -0.06
     название
    -0.06
    POSITIVE LOGITS
     Niagara
    0.09
    isini
    0.07
    (confirm
    0.07
    jl
    0.07
     �
    0.07
    며
    0.06
     perfor
    0.06
     fakt
    0.06
     porte
    0.06
    oric
    0.06
    Act Density 0.001%

    No Known Activations