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

    Neuronpedia

    INDEX
    Explanations

    evaluations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шибка
    -0.07
     bekommen
    -0.06
    .Username
    -0.06
    laps
    -0.06
    iculture
    -0.06
     обращ
    -0.06
    toMatch
    -0.06
     interacts
    -0.06
     kdyby
    -0.06
     }}/
    -0.06
    POSITIVE LOGITS
     Wildcats
    0.06
     Loving
    0.06
    Metro
    0.06
    -ce
    0.06
     اس
    0.06
     believer
    0.06
    _mode
    0.06
     doctrine
    0.06
     strom
    0.06
     coveted
    0.06
    Act Density 0.000%

    No Known Activations