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

    Neuronpedia

    INDEX
    Explanations

    Systems and deduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Metadata
    -0.07
     tego
    -0.06
     malware
    -0.06
    Э
    -0.06
    STA
    -0.06
    .area
    -0.06
     locator
    -0.06
    rpc
    -0.06
    _algo
    -0.06
    第四
    -0.06
    POSITIVE LOGITS
    صال
    0.07
    ederland
    0.07
     Francisco
    0.07
    stone
    0.07
    vangst
    0.07
    ileceği
    0.06
     zaháj
    0.06
     cerebral
    0.06
    ought
    0.06
     united
    0.06
    Act Density 0.038%

    No Known Activations