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

    Neuronpedia

    INDEX
    Explanations

    ew

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CCP
    -0.07
     humanitarian
    -0.07
     cộng
    -0.06
     AppCompatActivity
    -0.06
     Spaces
    -0.06
     tedbir
    -0.06
     FileInputStream
    -0.06
     Shelter
    -0.06
    .splitContainer
    -0.06
     APA
    -0.06
    POSITIVE LOGITS
    OW
    0.07
    inv
    0.07
    (phase
    0.07
     beim
    0.07
    days
    0.07
    dorf
    0.07
     kam
    0.06
    那样
    0.06
     careg
    0.06
     NGX
    0.06
    Act Density 0.009%

    No Known Activations