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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нового
    -0.07
    左
    -0.06
     Django
    -0.06
     Dummy
    -0.06
     qq
    -0.06
     Modular
    -0.06
    됨
    -0.05
     AssertionError
    -0.05
    YY
    -0.05
     psycopg
    -0.05
    POSITIVE LOGITS
     trails
    0.08
    quiries
    0.07
     haben
    0.07
    .small
    0.07
    iname
    0.06
    .signIn
    0.06
     passports
    0.06
     illnesses
    0.06
    osate
    0.06
     roll
    0.06
    Act Density 0.016%

    No Known Activations