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

    Neuronpedia

    INDEX
    Explanations

    couples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ═
    -0.06
     нам
    -0.06
    isiert
    -0.06
     알고
    -0.06
     domains
    -0.06
     nationalism
    -0.06
    त
    -0.06
     města
    -0.06
     tradi
    -0.06
     centre
    -0.06
    POSITIVE LOGITS
     Cory
    0.07
     keto
    0.07
     CPS
    0.07
    Allocation
    0.06
    /API
    0.06
    íně
    0.06
     Len
    0.06
    ADO
    0.06
    NavLink
    0.06
    compound
    0.06
    Act Density 0.000%

    No Known Activations