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

    Neuronpedia

    INDEX
    Explanations

    mass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حسن
    -0.07
     PROVIDED
    -0.07
     anesthesia
    -0.06
     Estado
    -0.06
     Reception
    -0.06
     одна
    -0.06
    _TOO
    -0.06
     chase
    -0.06
     succinct
    -0.06
     zdrav
    -0.06
    POSITIVE LOGITS
     Likewise
    0.08
     Miy
    0.07
     Carson
    0.07
    male
    0.07
     unstable
    0.07
    DllImport
    0.06
     Northwestern
    0.06
     cig
    0.06
     Ins
    0.06
    hue
    0.06
    Act Density 0.004%

    No Known Activations