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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     negligent
    -0.08
    eração
    -0.08
     Tire
    -0.07
    zenie
    -0.07
    ücken
    -0.07
     kontrol
    -0.06
    kelas
    -0.06
    수로
    -0.06
     лак
    -0.06
    tro
    -0.06
    POSITIVE LOGITS
     chic
    0.08
    Vintage
    0.07
    ConfigurationException
    0.07
    .shortcuts
    0.07
    .setState
    0.06
    ,_
    0.06
    Suddenly
    0.06
     Betting
    0.06
     Declarations
    0.06
     fucked
    0.06
    Act Density 0.000%

    No Known Activations