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

    Neuronpedia

    INDEX
    Explanations

    social welfare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    โก
    -0.07
     balances
    -0.07
    ्कर
    -0.07
    essages
    -0.06
     &=
    -0.06
    ห
    -0.06
     neckline
    -0.06
    ashtra
    -0.06
    Parse
    -0.06
    last
    -0.06
    POSITIVE LOGITS
    _dense
    0.06
     SignUp
    0.06
    traffic
    0.06
     والت
    0.06
    getField
    0.06
    ��
    0.06
     Už
    0.06
     choisir
    0.06
    urrences
    0.06
    abal
    0.06
    Act Density 0.035%

    No Known Activations