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

    Neuronpedia

    INDEX
    Explanations

    source code copyright notices

    np_max-act · gemini-2.0-flash

    The neuron activates on the literal token “USA.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Account
    -0.07
    MHz
    -0.07
    τικα
    -0.07
    mploy
    -0.07
     MHz
    -0.07
    出来
    -0.06
     Brid
    -0.06
    wdx
    -0.06
     حاصل
    -0.06
     Pages
    -0.06
    POSITIVE LOGITS
     tuz
    0.07
     Computes
    0.06
     pus
    0.06
    تيار
    0.06
     kari
    0.06
     ko
    0.06
     leg
    0.06
    odef
    0.05
     oder
    0.05
    .DOM
    0.05
    Act Density 0.004%

    No Known Activations