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

    Neuronpedia

    INDEX
    Explanations

    Numbers in the 100s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้เก
    -0.07
    regar
    -0.07
    代理
    -0.07
    xcc
    -0.07
    	dev
    -0.06
     Selector
    -0.06
     діт
    -0.06
    srv
    -0.06
     irrespective
    -0.06
     det
    -0.06
    POSITIVE LOGITS
     Option
    0.07
    izzle
    0.06
    .How
    0.06
    .Google
    0.06
    autical
    0.06
    ResponseBody
    0.06
    NB
    0.06
     cân
    0.06
    .Head
    0.06
    .Must
    0.06
    Act Density 0.038%

    No Known Activations